Skip to content
Back to search

arc-kit

SkillGitHubIncomplete

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/tractorjuice--arc-kit/badge.svg)](/listings/tractorjuice--arc-kit)

HTML

<a href="/listings/tractorjuice--arc-kit"><img src="/api/listings/tractorjuice--arc-kit/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Installation

**Claude Code** (premier experience) — install the ArcKit plugin (requires **v2.1.319+**):

First, make sure Claude Code is on the latest version:

claude install latest

Then in Claude Code:

/plugin marketplace add tractorjuice/arckit-claude

Then install from the Discover tab, or via CLI. The marketplace ships **20 plugins** — install only the overlays you need:

# Core (76 commands — UK Government civilian + generic enterprise)
claude plugin install arckit@arckit-claude

# Core + UAE federal
claude plugin install arckit arckit-uae

# Broad overlay set (UK + UAE + FR + CA + EU + AT + AU + US + UK-NHS + UK-GCloud)
claude plugin install arckit arckit-{uae,fr,ca,eu,at,au,us,uk-nhs,uk-gcloud}

# Enterprise architecture and AI agent governance overlays
claude plugin install arckit arckit-togaf-adm arckit-agent-architecture

The standalone `tractorjuice/arckit-claude` marketplace hosts all Claude Code plugins: the `arckit` core plugin, regional overlays, sector overlays, the TOGAF ADM, O-AA, arc42 and AI agent architecture overlays, the `arckit-fde` tooling plugin, and the public-but-proprietary `arckit-uk-gcloud` supplier overlay. The 18 community plugins (`arckit-uae`, `arckit-fr`, `arckit-nl`, `arckit-ca`, `arckit-eu`, `arckit-at`, `arckit-au`, `arckit-au-energy`, `arckit-us`, `arckit-uk-finance`, `arckit-uk-nhs`, `arckit-uk-legacy`, `arckit-uk-gcloud`, `arckit-togaf-adm`, `arckit-agent-architecture`, `arckit-oaa`, `arckit-arc42`, `arckit-repo`) require the `arckit` core plugin. `arckit-au-energy` (sector) additionally requires `arckit-au` (jurisdiction), which it composes — install with `claude plugin install arckit arckit-au arckit-au-energy`. `arckit-uk-gcloud` is a **proprietary, Claude Code only** supplier-side G-Cloud bid-authoring overlay — it is public for installation and inspection, but not MIT licensed and not distributed to the non-Claude extension formats. One **tooling plugin** — `arckit-fde` — is a lean, Claude Code only plugin with one command, `/arckit-fde:create`, that generates a brandable (white-label) Forward Deploy Engineering consulting website into `docs/` (GitHub Pages ready), with UK Public Sector and Generic market presets; no dependencies, not converted to non-Claude formats, no governance doc-types.

The older `tractorjuice/arc-kit` marketplace remains available for compatibility, but new Claude Code installs should use `tractorjuice/arckit-claude`. Claude Code is the **primary development platform** for ArcKit and provides the most complete experience: all official commands, autonomous research agents, automation hooks, bundled MCP servers (AWS Knowledge, Microsoft Learn, Google Developer Knowledge, govreposcrape, uk-tenders), and automatic updates via the marketplace. See [Why Claude Code?](#why-claude-code) below.

> **Why v2.1.319?** It closes three ways a command could get past a permission check or the sandbox. It also runs ArcKit's after-write steps on an artefact written just as you send a new message; earlier versions skipped them, so the artefact had no provenance block and no entry in the published index. And updating a plugin now installs a dependency the new version adds, which every overlay relies on for the core plugin. It still carries what v2.1.295 brought: `onFailure: "block"`, so a check on an ArcKit artefact stops the write when it can't run. It also carries the fix for plugin SessionStart hooks not running in new cloud sessions, which skipped ArcKit's session set-up and version check there. > > The floor also carries earlier releases ArcKit depends on: > > **Models** > > - **v2.1.284** adds **Claude Sonnet 5.5** (`claude-sonnet-5-5`), the default Sonnet model on the Anthropic API, with 1M context; earlier clients cannot select it. Like Opus 5.5 it always thinks and defaults to `effort: medium`, so ArcKit's `effort: max` commands run at `max` on it.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 451 lines
  1. {
  2. "name": "arc-kit",
  3. "owner": {
  4. "name": "TractorJuice",
  5. "email": "tractorjuice@users.noreply.github.com"
  6. },
  7. "metadata": {
  8. "description": "The Enterprise Architecture Governance Harness for Claude Code",
  9. "version": "1.0.0"
  10. },
  11. "plugins": [
  12. {
  13. "name": "arckit",
  14. "source": "./plugins/arckit-claude",
  15. "description": "76 slash commands across strategy, architecture, delivery, and assurance — including UK Government compliance",
  16. "version": "6.22.1",
  17. "author": {
  18. "name": "TractorJuice"
  19. },
  20. "homepage": "https://github.com/tractorjuice/arckit-claude",
  21. "repository": "https://github.com/tractorjuice/arckit-claude",
  22. "license": "MIT",
  23. "keywords": [
  24. "architecture",
  25. "governance",
  26. "enterprise",
  27. "procurement",
  28. "vendor-evaluation",
  29. "uk-government"
  30. ],
  31. "category": "productivity"
  32. },
  33. {
  34. "name": "arckit-uae",
  35. "source": "./plugins/arckit-uae",
  36. "description": "UAE Federal Overlay — 12 commands for PDPL, IAS, AI Charter, autonomy, sovereign cloud, UAE Pass",
  37. "version": "6.22.1",
  38. "author": {
  39. "name": "TractorJuice"
  40. },
  41. "homepage": "https://github.com/tractorjuice/arckit-claude",
  42. "repository": "https://github.com/tractorjuice/arckit-claude",
  43. "license": "MIT",
  44. "keywords": [
  45. "architecture",
  46. "governance",
  47. "uae",
  48. "compliance"
  49. ],
  50. "category": "productivity"
  51. },
  52. {
  53. "name": "arckit-fr",
  54. "source": "./plugins/arckit-fr",
  55. "description": "French Public Sector Overlay — 12 commands for DINUM, ANSSI, RGPD/CNIL, EBIOS, PSSI, SecNumCloud",
  56. "version": "6.22.1",
  57. "author": {
  58. "name": "TractorJuice"
  59. },
  60. "homepage": "https://github.com/tractorjuice/arckit-claude",
  61. "repository": "https://github.com/tractorjuice/arckit-claude",
  62. "license": "MIT",
  63. "keywords": [
  64. "architecture",
  65. "governance",
  66. "france",
  67. "anssi",
  68. "compliance"
  69. ],
  70. "category": "productivity"
  71. },
  72. {
  73. "name": "arckit-nl",
  74. "source": "./plugins/arckit-nl",
  75. "description": "Netherlands Public Sector Overlay — 6 commands for the Rijksbreed cloudbeleid 2026, Te Beschermen Belangen (TBB) category determination under VIRBI 2025, BIO2 conformance, cloud exit planning, and NORA and GEMMA reference-architecture assessments",
  76. "version": "6.22.1",
  77. "author": {
  78. "name": "TractorJuice"
  79. },
  80. "homepage": "https://github.com/tractorjuice/arckit-claude",
  81. "repository": "https://github.com/tractorjuice/arckit-claude",
  82. "license": "MIT",
  83. "keywords": [
  84. "architecture",
  85. "governance",
  86. "netherlands",
  87. "nora",
  88. "gemma",
  89. "cloud",
  90. "compliance"
  91. ],
  92. "category": "productivity"
  93. },
  94. {
  95. "name": "arckit-ca",
  96. "source": "./plugins/arckit-ca",
  97. "description": "Canadian Federal Overlay — 12 commands for AIA, ATIP, ITSG-33, GC Digital Standards, OCAP, OLA",
  98. "version": "6.22.1",
  99. "author": {
  100. "name": "TractorJuice"
  101. },
  102. "homepage": "https://github.com/tractorjuice/arckit-claude",
  103. "repository": "https://github.com/tractorjuice/arckit-claude",
  104. "license": "MIT",
  105. "keywords": [
  106. "architecture",
  107. "governance",
  108. "canada",
  109. "federal",
  110. "compliance"
  111. ],
  112. "category": "productivity"
  113. },
  114. {
  115. "name": "arckit-eu",
  116. "source": "./plugins/arckit-eu",
  117. "description": "EU Overlay — 8 commands for GDPR, AI Act, DSA, DORA, Data Act, NIS2, CRA, and the Cloud Sovereignty Framework",
  118. "version": "6.22.1",
  119. "author": {
  120. "name": "TractorJuice"
  121. },
  122. "homepage": "https://github.com/tractorjuice/arckit-claude",
  123. "repository": "https://github.com/tractorjuice/arckit-claude",
  124. "license": "MIT",
  125. "keywords": [
  126. "architecture",
  127. "governance",
  128. "eu",
  129. "compliance",
  130. "gdpr"
  131. ],
  132. "category": "productivity"
  133. },
  134. {
  135. "name": "arckit-at",
  136. "source": "./plugins/arckit-at",
  137. "description": "Austrian Overlay — 4 commands for DSG/DSGVO, NISG, Bundesvergabegesetz public procurement, and BaFG/WZG digital accessibility",
  138. "version": "6.22.1",
  139. "author": {
  140. "name": "TractorJuice"
  141. },
  142. "homepage": "https://github.com/tractorjuice/arckit-claude",
  143. "repository": "https://github.com/tractorjuice/arckit-claude",
  144. "license": "MIT",
  145. "keywords": [
  146. "architecture",
  147. "governance",
  148. "austria",
  149. "compliance"
  150. ],
  151. "category": "productivity"
  152. },
  153. {
  154. "name": "arckit-au",
  155. "source": "./plugins/arckit-au",
  156. "description": "Australian Federal Overlay — 10 commands for ASD Essential Eight, ISM, DTA DSS, Privacy Act 1988, OAIC NDB, PSPF, AI Assurance, DISP attestation, OT security, and SOCI/CIRMP",
  157. "version": "6.22.1",
  158. "author": {
  159. "name": "TractorJuice"
  160. },
  161. "homepage": "https://github.com/tractorjuice/arckit-claude",
  162. "repository": "https://github.com/tractorjuice/arckit-claude",
  163. "license": "MIT",
  164. "keywords": [
  165. "architecture",
  166. "governance",
  167. "australia",
  168. "compliance",
  169. "disp"
  170. ],
  171. "category": "productivity"
  172. },
  173. {
  174. "name": "arckit-au-energy",
  175. "source": "./plugins/arckit-au-energy",
  176. "description": "Australian Energy Sector Overlay — 2 commands for AESCSF maturity assessment and energy-sector compliance (AER ring-fencing, AEMC NER/NGR, AEMO interfaces, DERMS/DOE, CSIP-AUS, SOCI escalation). Recipe: au-energy. First Australian sector overlay; composes the arckit-au federal baseline. Requires arckit and arckit-au.",
  177. "version": "6.22.1",
  178. "author": {
  179. "name": "TractorJuice"
  180. },
  181. "homepage": "https://github.com/tractorjuice/arckit-claude",
  182. "repository": "https://github.com/tractorjuice/arckit-claude",
  183. "license": "MIT",
  184. "keywords": [
  185. "architecture",
  186. "governance",
  187. "australia",
  188. "energy",
  189. "aescsf",
  190. "critical-infrastructure",
  191. "aemo",
  192. "soci"
  193. ],
  194. "category": "productivity"
  195. },
  196. {
  197. "name": "arckit-us",
  198. "source": "./plugins/arckit-us",
  199. "description": "USA Federal Civilian Overlay — 10 commands for FedRAMP, FISMA/NIST 800-53, CISA Zero Trust, OMB M-19-17 ICAM, NIST AI RMF, OMB M-25-21/M-25-22 AI assurance, E-Gov §208 PIA, EO 14028 SBOM",
  200. "version": "6.22.1",
  201. "author": {
  202. "name": "TractorJuice"
  203. },
  204. "homepage": "https://github.com/tractorjuice/arckit-claude",
  205. "repository": "https://github.com/tractorjuice/arckit-claude",
  206. "license": "MIT",
  207. "keywords": [
  208. "architecture",
  209. "governance",
  210. "usa",
  211. "federal",
  212. "fedramp",
  213. "compliance"
  214. ],
  215. "category": "productivity"
  216. },
  217. {
  218. "name": "arckit-uk-finance",
  219. "source": "./plugins/arckit-uk-finance",
  220. "description": "UK Financial Services Payments Overlay — 4 commands for established UK PSPs / EMIs / PIs: PSD2 SCA-RTS exemption design, EMI/PI safeguarding, FCA Consumer Duty board report, Critical Third Parties dependency assessment. Recipe: uk-fs-payments. First sector-specific overlay.",
  221. "version": "6.22.1",
  222. "author": {
  223. "name": "TractorJuice"
  224. },
  225. "homepage": "https://github.com/tractorjuice/arckit-claude",
  226. "repository": "https://github.com/tractorjuice/arckit-claude",
  227. "license": "MIT",
  228. "keywords": [
  229. "architecture",
  230. "governance",
  231. "uk",
  232. "finance",
  233. "fca",
  234. "pra",
  235. "psd2",
  236. "sca-rts",
  237. "emi",
  238. "safeguarding",
  239. "consumer-duty",
  240. "ctp",
  241. "payments"
  242. ],
  243. "category": "productivity"
  244. },
  245. {
  246. "name": "arckit-uk-nhs",
  247. "source": "./plugins/arckit-uk-nhs",
  248. "description": "UK NHS Clinical Safety Overlay — 4 commands for NHS DCB0129 (manufacturer), DCB0160 (deployer), DTAC (form v2.0), and UK/EU MDR SaMD/AIaMD classification. Adopts Marcus Baw SAFETY.md spec. Second sector-specific overlay.",
  249. "version": "6.22.1",
  250. "author": {
  251. "name": "TractorJuice"
  252. },
  253. "homepage": "https://github.com/tractorjuice/arckit-claude",
  254. "repository": "https://github.com/tractorjuice/arckit-claude",
  255. "license": "MIT",
  256. "keywords": [
  257. "architecture",
  258. "governance",
  259. "uk",
  260. "nhs",
  261. "clinical-safety",
  262. "dcb0129",
  263. "dtac",
  264. "mdr",
  265. "samd",
  266. "healthcare"
  267. ],
  268. "category": "productivity"
  269. },
  270. {
  271. "name": "arckit-uk-legacy",
  272. "source": "./plugins/arckit-uk-legacy",
  273. "description": "UK Legacy IT Assessment Overlay — 1 command for evidence-led classification, independent numerical risk and actionable remediation. Includes frozen offline framework sources and a deterministic helper. Requires arckit core plugin.",
  274. "version": "6.22.1",
  275. "author": {
  276. "name": "TractorJuice"
  277. },
  278. "homepage": "https://github.com/tractorjuice/arckit-claude",
  279. "repository": "https://github.com/tractorjuice/arckit-claude",
  280. "license": "MIT",
  281. "keywords": [
  282. "architecture",
  283. "governance",
  284. "uk",
  285. "legacy-it",
  286. "risk",
  287. "remediation"
  288. ],
  289. "category": "productivity"
  290. },
  291. {
  292. "name": "arckit-fde",
  293. "source": "./plugins/arckit-fde",
  294. "description": "ArcKit FDE Site Generator — /arckit-fde:create interviews you and renders a brandable, GitHub-Pages-ready Forward Deploy Engineering consulting website to docs/. White-label brand, colour, pricing and contact; UK public sector or generic market preset. Claude Code only.",
  295. "version": "6.22.1",
  296. "author": {
  297. "name": "TractorJuice"
  298. },
  299. "homepage": "https://github.com/tractorjuice/arckit-claude",
  300. "repository": "https://github.com/tractorjuice/arckit-claude",
  301. "license": "MIT",
  302. "keywords": [
  303. "arckit",
  304. "fde",
  305. "forward-deploy-engineering",
  306. "website",
  307. "site-generator",
  308. "consulting",
  309. "white-label",
  310. "github-pages",
  311. "marketing-site"
  312. ],
  313. "category": "productivity"
  314. },
  315. {
  316. "name": "arckit-repo",
  317. "source": "./plugins/arckit-repo",
  318. "description": "Repository tooling plugin for ArcKit. /arckit:repo-docs generates source-grounded, agent-readable repository documentation; /arckit:repo-audit audits a codebase (local or public GitHub/GitLab) against architecture principles and requirements. Requires arckit core. [COMMUNITY]",
  319. "version": "6.22.1",
  320. "author": {
  321. "name": "ArcKit Contributors"
  322. },
  323. "homepage": "https://github.com/tractorjuice/arckit-claude",
  324. "repository": "https://github.com/tractorjuice/arckit-claude",
  325. "license": "MIT",
  326. "keywords": [
  327. "architecture",
  328. "governance",
  329. "repository",
  330. "git",
  331. "documentation",
  332. "agents",
  333. "openwiki",
  334. "audit",
  335. "codebase"
  336. ],
  337. "category": "productivity"
  338. },
  339. {
  340. "name": "arckit-uk-gcloud",
  341. "source": "./plugins/arckit-uk-gcloud",
  342. "description": "UK G-Cloud Supplier Bid-Authoring Overlay — 15 supplier-side commands driving a G-Cloud 15 (RM1557.15) Digital Marketplace submission end to end: supplier profile, social value, lot questions, Procurement Act 2023 declaration, service design, Service Definition Documents (Lots 1a/1b/2a/2b/3), pricing, security evidence, competitor benchmark, submission review, and GCA submission packaging. Recipe: uk-gcloud-submission. Requires arckit core. Proprietary, experimental.",
  343. "version": "6.22.1",
  344. "author": {
  345. "name": "TractorJuice"
  346. },
  347. "homepage": "https://github.com/tractorjuice/arckit-claude",
  348. "repository": "https://github.com/tractorjuice/arckit-claude",
  349. "license": "Proprietary",
  350. "keywords": [
  351. "architecture",
  352. "governance",
  353. "uk",
  354. "gcloud",
  355. "g-cloud",
  356. "digital-marketplace",
  357. "g-cloud-15",
  358. "gca",
  359. "government-commercial-agency",
  360. "ccs",
  361. "social-value",
  362. "procurement-act-2023",
  363. "procurement",
  364. "supplier",
  365. "sdd",
  366. "bid"
  367. ],
  368. "category": "productivity"
  369. },
  370. {
  371. "name": "arckit-togaf-adm",
  372. "source": "./plugins/arckit-togaf-adm",
  373. "description": "TOGAF ADM — Enterprise Architecture Development Method. 9 commands covering all ADM phases (Preliminary through H) plus Architecture Repository. [COMMUNITY]",
  374. "version": "6.22.1",
  375. "author": {
  376. "name": "ArcKit Contributors"
  377. },
  378. "homepage": "https://github.com/tractorjuice/arckit-claude",
  379. "repository": "https://github.com/tractorjuice/arckit-claude",
  380. "license": "MIT",
  381. "keywords": [
  382. "architecture",
  383. "governance",
  384. "togaf",
  385. "adm",
  386. "enterprise-architecture"
  387. ],
  388. "category": "productivity"
  389. },
  390. {
  391. "name": "arckit-agent-architecture",
  392. "source": "./plugins/arckit-agent-architecture",
  393. "description": "AI Agent Architecture — Governance, design, and security for autonomous AI agent programs. 6 commands. [COMMUNITY]",
  394. "version": "6.22.1",
  395. "author": {
  396. "name": "ArcKit Contributors"
  397. },
  398. "homepage": "https://github.com/tractorjuice/arckit-claude",
  399. "repository": "https://github.com/tractorjuice/arckit-claude",
  400. "license": "MIT",
  401. "keywords": [
  402. "architecture",
  403. "governance",
  404. "ai",
  405. "agents",
  406. "agent-architecture"
  407. ],
  408. "category": "productivity"
  409. },
  410. {
  411. "name": "arckit-oaa",
  412. "source": "./plugins/arckit-oaa",
  413. "description": "Open Agile Architecture (O-AA) — agile enterprise architecture for product-driven, sprint-based delivery. 5 commands: ADM Lite, Product Architecture, Agile Strategy, Agile Security, Agile Governance. [COMMUNITY]",
  414. "version": "6.22.1",
  415. "author": {
  416. "name": "ArcKit Contributors"
  417. },
  418. "homepage": "https://github.com/tractorjuice/arckit-claude",
  419. "repository": "https://github.com/tractorjuice/arckit-claude",
  420. "license": "MIT",
  421. "keywords": [
  422. "architecture",
  423. "governance",
  424. "agile",
  425. "oaa",
  426. "enterprise-architecture"
  427. ],
  428. "category": "productivity"
  429. },
  430. {
  431. "name": "arckit-arc42",
  432. "source": "./plugins/arckit-arc42",
  433. "description": "arc42 overlay for ArcKit. /arckit:arc42 assembles an arc42 architecture description from the project's existing artefacts, citing each source and listing uncovered sections in a Gap Register; /arckit:arc42-quality, /arckit:arc42-concepts and /arckit:arc42-debt write its sections 10, 8 and 11.2; /arckit:arc42-handover hands it over to Spec Kit. Recipe: arc42-full. Requires arckit core. [COMMUNITY]",
  434. "version": "6.22.1",
  435. "author": {
  436. "name": "ArcKit Contributors"
  437. },
  438. "homepage": "https://github.com/tractorjuice/arckit-claude",
  439. "repository": "https://github.com/tractorjuice/arckit-claude",
  440. "license": "MIT AND CC-BY-SA-4.0",
  441. "keywords": [
  442. "architecture",
  443. "governance",
  444. "arc42",
  445. "documentation",
  446. "architecture-description"
  447. ],
  448. "category": "productivity"
  449. }
  450. ]
  451. }
README.md · README · 2,137 lines
  1. # ArcKit: The Enterprise Architecture Governance Harness
  2. [![GitHub Stars](https://img.shields.io/github/stars/tractorjuice/arc-kit?style=flat&logo=github)](https://github.com/tractorjuice/arc-kit/stargazers)
  3. [![GitHub Forks](https://img.shields.io/github/forks/tractorjuice/arc-kit?style=flat&logo=github)](https://github.com/tractorjuice/arc-kit/network/members)
  4. [![License: MIT](https://img.shields.io/github/license/tractorjuice/arc-kit)](LICENSE)
  5. [![Latest Release](https://img.shields.io/github/v/release/tractorjuice/arc-kit)](https://github.com/tractorjuice/arc-kit/releases)
  6. [![GitHub Issues](https://img.shields.io/github/issues/tractorjuice/arc-kit)](https://github.com/tractorjuice/arc-kit/issues)
  7. ![ArcKit: The Enterprise Architecture Governance Harness](docs/assets/arckit-banner-light.svg)
  8. **Build better enterprise architecture through structured strategy, design, delivery, and assurance workflows.**
  9. ArcKit is a toolkit for enterprise architects that transforms architecture governance from scattered documents into a systematic, AI-assisted workflow for:
  10. - 🏛️ Establishing and enforcing architecture principles
  11. - 👥 Analyzing stakeholder drivers, goals, and outcomes
  12. - 🛡️ Risk management (HM Treasury Orange Book)
  13. - 💼 Business case justification (HM Treasury Green Book SOBC)
  14. - 📋 Creating comprehensive requirements documents
  15. - 🗄️ Data modeling with ERD, GDPR compliance, and data governance
  16. - 🔬 Technology research: options, checked facts and published costs (web search powered)
  17. - ☁️ Azure-specific research using Microsoft Learn MCP for authoritative documentation
  18. - 🗺️ Strategic planning with Wardley Mapping
  19. - 📊 Generating visual architecture diagrams (Mermaid)
  20. - 🤝 Managing vendor RFP and selection processes
  21. - ✅ Conducting formal design reviews (HLD/DLD)
  22. - 🔧 ServiceNow service management design
  23. - 🔗 Maintaining requirements traceability
  24. - 📎 Citation traceability for external documents (inline `[DOC-CN]` markers with source quotes)
  25. > ArcKit produces **DRAFT artefacts for qualified people to review**, not legal, regulatory, clinical, or security advice. See [What ArcKit does not do](#what-arckit-does-not-do).
  26. ## Watch first
  27. New to ArcKit, or explaining it to someone who doesn't use a coding assistant? Start with a film:
  28. - [ArcKit explained](https://youtu.be/-oQ5VRpkxp0): what ArcKit is and how it keeps AI-drafted architecture documents reviewable, in under eight minutes.
  29. - [ArcKit for Beginners](https://www.youtube.com/playlist?list=PLHAFN5RjB5As): one fictional council project, followed from its architecture principles to the release decision. One hour, or four shorter parts.
  30. - [ArcKit commands](https://www.youtube.com/playlist?list=PLOxB2ULF5XX0): a film of about a minute and a half for each command: what it is for, when to run it and what it produces.
  31. The [ArcKit YouTube channel](https://www.youtube.com/@arckitorg/playlists) also has a playlist for each overlay. The narration is AI-generated and the films are experimental; tell us on [Discord](https://discord.gg/HsA4Y3hQ4) what to cover next.
  32. ---
  33. ## Quick Start
  34. ### Installation
  35. **Claude Code** (premier experience) — install the ArcKit plugin (requires **v2.1.319+**):
  36. First, make sure Claude Code is on the latest version:
  37. ```bash
  38. claude install latest
  39. ```
  40. Then in Claude Code:
  41. ```text
  42. /plugin marketplace add tractorjuice/arckit-claude
  43. ```
  44. Then install from the Discover tab, or via CLI. The marketplace ships **20 plugins** — install only the overlays you need:
  45. ```bash
  46. # Core (76 commands — UK Government civilian + generic enterprise)
  47. claude plugin install arckit@arckit-claude
  48. # Core + UAE federal
  49. claude plugin install arckit arckit-uae
  50. # Broad overlay set (UK + UAE + FR + CA + EU + AT + AU + US + UK-NHS + UK-GCloud)
  51. claude plugin install arckit arckit-{uae,fr,ca,eu,at,au,us,uk-nhs,uk-gcloud}
  52. # Enterprise architecture and AI agent governance overlays
  53. claude plugin install arckit arckit-togaf-adm arckit-agent-architecture
  54. ```
  55. The standalone `tractorjuice/arckit-claude` marketplace hosts all Claude Code plugins: the `arckit` core plugin, regional overlays, sector overlays, the TOGAF ADM, O-AA, arc42 and AI agent architecture overlays, the `arckit-fde` tooling plugin, and the public-but-proprietary `arckit-uk-gcloud` supplier overlay. The 18 community plugins (`arckit-uae`, `arckit-fr`, `arckit-nl`, `arckit-ca`, `arckit-eu`, `arckit-at`, `arckit-au`, `arckit-au-energy`, `arckit-us`, `arckit-uk-finance`, `arckit-uk-nhs`, `arckit-uk-legacy`, `arckit-uk-gcloud`, `arckit-togaf-adm`, `arckit-agent-architecture`, `arckit-oaa`, `arckit-arc42`, `arckit-repo`) require the `arckit` core plugin. `arckit-au-energy` (sector) additionally requires `arckit-au` (jurisdiction), which it composes — install with `claude plugin install arckit arckit-au arckit-au-energy`. `arckit-uk-gcloud` is a **proprietary, Claude Code only** supplier-side G-Cloud bid-authoring overlay — it is public for installation and inspection, but not MIT licensed and not distributed to the non-Claude extension formats. One **tooling plugin** — `arckit-fde` — is a lean, Claude Code only plugin with one command, `/arckit-fde:create`, that generates a brandable (white-label) Forward Deploy Engineering consulting website into `docs/` (GitHub Pages ready), with UK Public Sector and Generic market presets; no dependencies, not converted to non-Claude formats, no governance doc-types.
  56. The older `tractorjuice/arc-kit` marketplace remains available for compatibility, but new Claude Code installs should use `tractorjuice/arckit-claude`. Claude Code is the **primary development platform** for ArcKit and provides the most complete experience: all official commands, autonomous research agents, automation hooks, bundled MCP servers (AWS Knowledge, Microsoft Learn, Google Developer Knowledge, govreposcrape, uk-tenders), and automatic updates via the marketplace. See [Why Claude Code?](#why-claude-code) below.
  57. > **Why v2.1.319?** It closes three ways a command could get past a permission check or the sandbox. It also runs ArcKit's after-write steps on an artefact written just as you send a new message; earlier versions skipped them, so the artefact had no provenance block and no entry in the published index. And updating a plugin now installs a dependency the new version adds, which every overlay relies on for the core plugin. It still carries what v2.1.295 brought: `onFailure: "block"`, so a check on an ArcKit artefact stops the write when it can't run. It also carries the fix for plugin SessionStart hooks not running in new cloud sessions, which skipped ArcKit's session set-up and version check there.
  58. >
  59. > The floor also carries earlier releases ArcKit depends on:
  60. >
  61. > **Models**
  62. >
  63. > - **v2.1.284** adds **Claude Sonnet 5.5** (`claude-sonnet-5-5`), the default Sonnet model on the Anthropic API, with 1M context; earlier clients cannot select it. Like Opus 5.5 it always thinks and defaults to `effort: medium`, so ArcKit's `effort: max` commands run at `max` on it.
  64. > - **v2.1.280** adds **Claude Opus 5.5** (`claude-opus-5-5`), the default Opus model. It always thinks, so ArcKit's `effort: max` commands can no longer be quietly sent as `high` by a session with thinking off, and the Effective Effort row in each artefact's Build Provenance is accurate.
  65. > - **v2.1.219** adds **Claude Opus 5** (`claude-opus-5`), with 1M context and fast mode, which earlier clients cannot select (superseded as the default by Opus 5.5).
  66. > - **v2.1.197** makes Claude Sonnet 5 the default, with native 1M context.
  67. >
  68. > **Security and permissions**
  69. >
  70. > - **v2.1.251** stops the file tools (Read, Write, Edit) following a symlink swapped inside the working directory *after* the permission check, and makes Grep and Glob honour `Read()` deny rules through a symlinked search path. That is the same class of bypass the v2.1.222–v2.1.224 fixes closed for Bash, and the class ArcKit's `file-protection` and `secret-file-scanner` gates sit in front of.
  71. > - **v2.1.234** stops Claude Code's MCP diagnostics printing **resolved secrets**. ArcKit bundles two keyed MCP servers whose `${user_config.*}` API keys sit in request headers. On a session with no keys configured those connections fail *by design*, so ArcKit routinely produces exactly the diagnostics this fixed.
  72. > - **v2.1.222** stops PreToolUse auto-allow hooks bypassing tool restrictions inside background agent tasks, which became load-bearing when v2.1.232 made subagent spawns background by default.
  73. > - **v2.1.223 and v2.1.224** close Bash permission-check bypasses, a sandbox `denyRead`/`denyWrite` trailing-slash bypass, and a bug where project paths over 200 characters resolved into another project's session directory. v2.1.224 also surfaces sandbox violation details in Bash results.
  74. > - **v2.1.172** fixes wildcard-domain `WebFetch` rules (`WebFetch(domain:*.gov.uk)`) that never matched subdomains on earlier clients. That is the exact shape ArcKit recommends for confining research-agent traffic in OFFICIAL-SENSITIVE deployments.
  75. >
  76. > **Effort and thinking**
  77. >
  78. > - **v2.1.251** sends Opus 5 `effort: xhigh`/`max` as `high` when thinking is off instead of failing, so ArcKit's `effort: max` commands complete on thinking-off sessions.
  79. > - **v2.1.221** fixes `WebSearch` returning a 400 at `effort: xhigh`/`max` when thinking is disabled, which silently broke ArcKit's `effort: max` commands and its three max-effort research agents for anyone running with thinking off.
  80. >
  81. > **Plugin loading and agents**
  82. >
  83. > - **v2.1.246** fixes four plugin-loading bugs that hit ArcKit's exact layout: `/reload-plugins` counted 0 skills for plugins that define skills under `skills/*/SKILL.md`, hook error messages showed a literal `${CLAUDE_PLUGIN_ROOT}` instead of the resolved path, the plugin cache created duplicate SHA-named directories, and `claude plugin update <bare-name>` failed.
  84. > - **v2.1.200** fixes project-scoped plugin loading from git worktrees and `claude agents --plugin-dir <dir>` visibility, which makes ArcKit's branch and test-repo workflows reliable.
  85. > - **v2.1.198–v2.1.199** fix background-subagent reliability, parent error propagation and hook stderr visibility, which matter to `/arckit:build`, reader/writer handoffs and hook diagnosis.
  86. >
  87. > **Older fixes:** v2.1.156 Opus 4.8 thinking-block fix, v2.1.154 plugin `defaultEnabled: false`, v2.1.144 session-title and headless Skill tool fixes, v2.1.143 plugin dependency enforcement, v2.1.139 hook `args: string[]`, v2.1.129 monitor layout and prompt-cache fixes, v2.1.121 MCP/provenance hook unlocks, v2.1.118–v2.1.119 release/telemetry unlocks, and the earlier `/context`, Auto mode, plugin update, MCP leak, retry and subagent working-directory fixes.
  88. **Gemini CLI** — install the ArcKit extension:
  89. ```bash
  90. gemini extensions install https://github.com/tractorjuice/arckit-gemini
  91. ```
  92. Zero-config: all 76 official commands, templates, scripts, and bundled MCP servers (AWS Knowledge, Microsoft Learn). Updates via `gemini extensions update arckit`.
  93. **GitHub Copilot** (VS Code) — install the ArcKit CLI and scaffold prompt files:
  94. ```bash
  95. # Install with pip
  96. pip install git+https://github.com/tractorjuice/arc-kit.git
  97. # Scaffold a project with Copilot prompt files
  98. arckit init my-project --ai copilot
  99. ```
  100. Creates `.github/prompts/arckit-*.prompt.md` (165 prompt files — the 76 official commands plus the community overlays), `.github/agents/arckit-*.agent.md` (10 custom agents), and `.github/copilot-instructions.md` (repo-wide context). Invoke commands in Copilot Chat as `/arckit-requirements`, `/arckit-stakeholders`, etc.
  101. **Codex CLI** — install the ArcKit CLI:
  102. ```bash
  103. # Install with pip
  104. pip install git+https://github.com/tractorjuice/arc-kit.git
  105. # Or with uv
  106. uv tool install arckit-cli --from git+https://github.com/tractorjuice/arc-kit.git
  107. # Or run without installing
  108. uvx --from git+https://github.com/tractorjuice/arc-kit.git arckit init my-project
  109. ```
  110. **Mistral Vibe CLI** — link the ArcKit extension:
  111. ```bash
  112. # Clone the standalone extension repository
  113. git clone https://github.com/tractorjuice/arckit-vibe.git
  114. cd arckit-vibe
  115. # Create extensions directory and link
  116. mkdir -p ~/.vibe/extensions/
  117. ln -s $(pwd) ~/.vibe/extensions/arckit
  118. ```
  119. Zero-config: 76 official commands as skills, 10 specialized agents, all templates, and bundled MCP servers (AWS Knowledge, Microsoft Learn, Google Developer Knowledge, GovRepoScrape).
  120. **Kimi Code CLI** — start `kimi`, then install the ArcKit plugin from the prompt:
  121. ```text
  122. /plugins install https://github.com/tractorjuice/arckit-kimi.git
  123. ```
  124. Every ArcKit command ships as an Agent Skill, invoked with `/skill:arckit-<command>` (for example `/skill:arckit-requirements`). The `kimi.plugin.json` manifest carries all six bundled MCP servers and auto-loads the `architecture-workflow` skill at session start.
  125. **Latest Release**: [v6.22.1](https://github.com/tractorjuice/arc-kit/releases/tag/v6.22.1)
  126. ### OKF Interoperability
  127. ArcKit can exchange Markdown knowledge bundles using an Open Knowledge Format-shaped frontmatter layer:
  128. - `/arckit:export-okf` copies ArcKit `ARC-*.md` artifacts into an OKF bundle with portable `type`, `title`, `resource`, `tags`, `timestamp`, and `arckit` metadata.
  129. - `/arckit:import-okf` scans an OKF bundle, writes `.arckit/tmp/okf-import-report.json`, and materializes safe imports as `RSCH` review notes by default.
  130. - Native ArcKit files remain unchanged unless you explicitly enable source frontmatter stamping with `ARCKIT_OKF_FRONTMATTER=1` or `.arckit/config.json` containing `{ "okfFrontmatter": true }`.
  131. ### Platform Support
  132. | Platform | Claude Code Plugin | Gemini CLI Extension | GitHub Copilot | Codex / OpenCode CLI | Mistral Vibe | Kimi Code CLI |
  133. |----------|-------------------|---------------------|----------------|---------------------|--------------|----------------|
  134. | macOS | Full support | Full support | Full support | Full support | Full support | Full support |
  135. | Linux | Full support | Full support | Full support | Full support | Full support | Full support |
  136. | Windows (WSL2) | Full support | Full support | Full support | Full support | Full support | Full support |
  137. | Windows (native) | Full support | Full support | Full support | Partial | Full support | Full support |
  138. **Windows users**: The Claude Code plugin, Gemini CLI extension, GitHub Copilot prompt files, Mistral Vibe extension, and Kimi Code CLI extension work natively on all platforms. For Codex CLI / OpenCode CLI on native Windows (without WSL), some commands containing inline bash snippets may require [Git Bash](https://git-scm.com/downloads/win) or [WSL2](https://learn.microsoft.com/en-us/windows/wsl/install). We recommend WSL2 for the best experience.
  139. ### Initialize a Project
  140. **Claude Code**: No initialization needed — the plugin provides everything.
  141. **Mistral Vibe**: No initialization needed — the extension provides everything.
  142. **Kimi Code CLI**:
  143. ```bash
  144. # Create a new architecture governance project
  145. arckit init payment-modernization --ai kimi
  146. # Or initialize in current directory
  147. arckit init . --ai kimi
  148. ```
  149. **GitHub Copilot** (VS Code):
  150. ```bash
  151. # Create a new architecture governance project
  152. arckit init payment-modernization --ai copilot
  153. # Or initialize in current directory
  154. arckit init . --ai copilot
  155. ```
  156. **OpenCode CLI**:
  157. ```bash
  158. # Create a new architecture governance project
  159. arckit init payment-modernization --ai opencode
  160. # Or initialize in current directory
  161. arckit init . --ai opencode
  162. ```
  163. **Codex CLI**:
  164. ```bash
  165. # Create a new architecture governance project
  166. arckit init payment-modernization --ai codex
  167. # Minimal install (skip docs and guides)
  168. arckit init payment-modernization --ai codex --minimal
  169. # Or initialize in current directory
  170. arckit init . --ai codex
  171. ```
  172. ### Start Using ArcKit
  173. ```bash
  174. # GitHub Copilot (VS Code)
  175. cd payment-modernization && code .
  176. # In Copilot Chat, use ArcKit commands:
  177. /arckit-principles Create principles for a financial services company
  178. /arckit-requirements Build a payment processing system...
  179. # Codex CLI
  180. cd payment-modernization
  181. codex
  182. # Inside your AI assistant, use ArcKit commands:
  183. /arckit:principles Create principles for a financial services company
  184. /arckit:requirements Build a payment processing system...
  185. /arckit:sow Generate RFP for vendor selection
  186. # Mistral Vibe CLI
  187. cd payment-modernization
  188. vibe
  189. # Use ArcKit skills:
  190. /arckit-principles Create principles for a financial services company
  191. /arckit-requirements Build a payment processing system...
  192. /arckit-sow Generate RFP for vendor selection
  193. # Or use specialized agents:
  194. vibe --agent arckit-research "Research cloud providers"
  195. # Kimi Code CLI
  196. cd payment-modernization
  197. kimi
  198. # Use ArcKit skills:
  199. /skill:arckit-principles Create principles for a financial services company
  200. /skill:arckit-requirements Build a payment processing system...
  201. /skill:arckit-sow Generate RFP for vendor selection
  202. ```
  203. ### Upgrading
  204. **Claude Code plugin**: Updates are automatic via the marketplace — no action needed.
  205. **Gemini CLI extension**: Updates via `gemini extensions update arckit`.
  206. **GitHub Copilot**: Re-run `arckit init --here --ai copilot` to update prompt files, agents, and instructions.
  207. **Mistral Vibe**: Pull the latest standalone extension repo: `cd ~/.vibe/extensions/arckit && git pull`.
  208. **Kimi Code CLI**: Re-run the install command from the `kimi` prompt to pick up the latest release: `/plugins install https://github.com/tractorjuice/arckit-kimi.git`.
  209. **Codex CLI**:
  210. ```bash
  211. # Step 1: Upgrade the CLI tool
  212. pip install --upgrade git+https://github.com/tractorjuice/arc-kit.git
  213. # Or with uv:
  214. uv tool install --force arckit-cli --from git+https://github.com/tractorjuice/arc-kit.git
  215. # Step 2: Update your existing project (re-run init in place)
  216. cd /path/to/your-existing-project
  217. arckit init --here --ai codex
  218. ```
  219. This updates commands, templates, scripts, and agents while **preserving** your project data (`projects/`) and custom templates (`.arckit/templates-custom/`).
  220. If upgrading from v0.x, you may also need to migrate legacy filenames — see the [upgrading guide](docs/guides/upgrading.md) for full details.
  221. ---
  222. ### Explore Example Outputs
  223. Public demonstration repositories showcase complete ArcKit deliverables:
  224. - **NHS Appointment Booking** — [arckit-test-project-v7-nhs-appointment](https://github.com/tractorjuice/arckit-test-project-v7-nhs-appointment): Digital health platform with NHS Spine integration and GDPR safeguards.
  225. - **M365 GCC-H Migration** — [arckit-test-project-v1-m365](https://github.com/tractorjuice/arckit-test-project-v1-m365): Government cloud migration with compliance mapping and change management.
  226. - **HMRC Tax Assistant** — [arckit-test-project-v2-hmrc-chatbot](https://github.com/tractorjuice/arckit-test-project-v2-hmrc-chatbot): Conversational AI service covering PII protection and bilingual support.
  227. - **Windows 11 Deployment** — [arckit-test-project-v3-windows11](https://github.com/tractorjuice/arckit-test-project-v3-windows11): Enterprise OS rollout with policy migration and security baselines.
  228. - **Patent Application System** — [arckit-test-project-v6-patent-system](https://github.com/tractorjuice/arckit-test-project-v6-patent-system): Intellectual property workflow automation using GOV.UK Pay and Notify.
  229. - **ONS Data Platform** — [arckit-test-project-v8-ons-data-platform](https://github.com/tractorjuice/arckit-test-project-v8-ons-data-platform): Official statistics analytics environment with Five Safes governance.
  230. - **Cabinet Office GenAI Platform** — [arckit-test-project-v9-cabinet-office-genai](https://github.com/tractorjuice/arckit-test-project-v9-cabinet-office-genai): Cross-government GenAI platform with responsible AI guardrails.
  231. - **UK Government Training Marketplace** — [arckit-test-project-v10-training-marketplace](https://github.com/tractorjuice/arckit-test-project-v10-training-marketplace): AI training procurement platform with multi-sided marketplace design.
  232. - **National Highways Data Architecture** — [arckit-test-project-v11-national-highways-data](https://github.com/tractorjuice/arckit-test-project-v11-national-highways-data): Strategic road network data platform modernization.
  233. - **Scottish Courts GenAI** — [arckit-test-project-v14-scottish-courts](https://github.com/tractorjuice/arckit-test-project-v14-scottish-courts): Scottish Courts and Tribunals Service GenAI strategy with comprehensive MLOps and FinOps.
  234. - **Doctors Appointment System** — [arckit-test-project-v16-doctors-appointment](https://github.com/tractorjuice/arckit-test-project-v16-doctors-appointment): Online appointment booking system with NHS integration.
  235. - **UK Fuel Price Transparency** — [arckit-test-project-v17-fuel-prices](https://github.com/tractorjuice/arckit-test-project-v17-fuel-prices): UK Government fuel price transparency service with real-time pricing data.
  236. - **Smart Meter Consumer App** — [arckit-test-project-v18-smart-meter](https://github.com/tractorjuice/arckit-test-project-v18-smart-meter): UK Smart Meter data consumer mobile app with DCC/SMIP integration.
  237. - **UK Government API Aggregator** — [arckit-test-project-v19-gov-api-aggregator](https://github.com/tractorjuice/arckit-test-project-v19-gov-api-aggregator): Unified access to 240+ UK Government APIs across 34+ departments.
  238. ---
  239. ## What it costs (plugin footprint)
  240. Token cost of installing the `arckit` core plugin in a Claude Code session, captured from `claude plugin details arckit` on v2.1.143+:
  241. - **Always-on per session: ~10,042 tokens** — added to every session's system context, covering the 73 command-skills + 5 utility skills (`architecture-workflow`, `arckit-build`, `mermaid-syntax`, `plantuml-syntax`, `wardley-mapping`) + 29 agent descriptors. Hooks (9 events) and MCP servers (6) are harness-resolved at runtime and not counted.
  242. - **On-invoke: ~250 to ~60K tokens per command** — paid only when a specific skill or agent fires. Most commands are in the 5–10K range.
  243. ### On-invoke cost by command
  244. Costs are estimates from the Claude Code tokenizer and may differ from actual usage. Use this table to budget research-heavy multi-command sessions.
  245. | Tier | Range | Commands |
  246. |------|-------|----------|
  247. | Lightweight | <2K | `start`, `init`, `build`, `search`, `impact`, `navigator`, `graph-report`, `framework`, `gov-landscape`, `aws-research`, `azure-research`, `gcp-research` |
  248. | Standard | 2–7K | `customize`, `score`, `principles`, `mermaid-syntax`, `plantuml-syntax`, `architecture-workflow`, `datascout`, `tenders`, `competitors`, `evaluate`, `hld-review`, `mlops`, `devops`, `finops`, `research`, `tcop`, `wardley-mapping`, `template-builder`, `glossary`, `dld-review`, `traceability`, `stakeholders`, `presentation`, `dfd`, `operationalize`, `requirements`, `maturity-model`, `data-model`, `gov-reuse`, `strategy`, `presentation`, `atrs`, `gov-code-search` |
  249. | Heavy | 7–15K | `wardley.value-chain`, `gcloud-clarify`, `ai-playbook`, `sow`, `sobc`, `risk`, `secure`, `dpia`, `dos`, `mod-secure`, `plan`, `conformance`, `roadmap`, `health`, `wardley.doctrine`, `wardley.gameplay`, `pages`, `servicenow`, `gcloud-search`, `principles-compliance`, `story`, `wardley`, `wardley.climate`, `data-mesh-contract`, `platform-design`, `adr`, `arckit-build`, `grants` |
  250. | Research-heavy | 15–25K | `service-assessment`, `analyze`, `backlog`, `diagram` |
  251. | Specialist | >25K | `jsp-936` (~60K — MOD JSP 936 AI assurance, defence-only) |
  252. ### Trimming the footprint
  253. - The five utility skills already use `paths:` globs to scope their always-on cost to relevant projects (`mermaid-syntax` only loads under `*.mmd`, `wardley-mapping` under WARD artefacts, etc.). The 73 command-skills are listed but not described in detail in the always-on context — the full prompt only loads on invocation.
  254. - Community overlays (`arckit-uae`, `arckit-fr`, `arckit-nl`, `arckit-ca`, `arckit-eu`, `arckit-at`, `arckit-au`, `arckit-au-energy`, `arckit-us`, `arckit-uk-finance`, `arckit-uk-nhs`) are independent plugins — install only the jurisdictions / sectors you need. Each adds its own always-on baseline. `arckit-uk-finance`, `arckit-uk-nhs`, and `arckit-au-energy` are **sector** overlays (`arckit-au-energy` layers the energy sector on the `arckit-au` jurisdiction baseline); the rest are jurisdiction-based.
  255. - Heavy commands (`jsp-936`, `analyze`, `diagram`, `backlog`) are on-invoke only; the always-on cost is unaffected by which heavy commands exist.
  256. To measure your own session footprint, run `/context all` (Claude Code v2.1.139+) for per-skill token estimates against your active model.
  257. ---
  258. ## Why ArcKit?
  259. ### Problem: Architecture Governance is Broken
  260. Traditional enterprise architecture suffers from:
  261. - ❌ Scattered documents across tools (Word, Confluence, PowerPoint)
  262. - ❌ Inconsistent governance enforcement
  263. - ❌ Manual vendor evaluation with bias
  264. - ❌ Lost traceability between requirements and design
  265. - ❌ Stale documentation that doesn't match reality
  266. ### Solution: Structured, AI-Assisted Governance
  267. ArcKit provides:
  268. - ✅ **Template-Driven Quality**: Comprehensive templates ensure nothing is forgotten
  269. - ✅ **Systematic Workflows**: Clear processes from requirements → procurement → design review
  270. - ✅ **AI Assistance**: Let AI handle document generation, you focus on decisions
  271. - ✅ **Enforced Traceability**: Automatic gap detection and coverage analysis
  272. - ✅ **Version Control**: Git-based workflow for all architecture artifacts
  273. ---
  274. ## What ArcKit does not do
  275. ArcKit generates **DRAFT artefacts for qualified people to review**. It is not legal, regulatory, clinical, or security advice, and no output it produces is a submission, a certification, an accreditation, or a compliance decision. Every artefact carries `Status: DRAFT` until a named accountable person signs it off, and that is the point at which responsibility for the content transfers to your organisation.
  276. Concretely, and regardless of how complete an artefact looks:
  277. - **A `/arckit:dpia` output is not a completed DPIA.** UK GDPR Article 35 places the assessment on the controller, and Article 36 requires prior consultation with the ICO where high residual risk remains. ArcKit drafts the document. The controller and the Data Protection Officer own it, and only they can conclude it.
  278. - **`/arckit:secure` and `/arckit:mod-secure` do not produce an assurance decision.** NCSC CAF outcomes, Cyber Essentials certification, and MOD Secure by Design assurance are all judged by named accountable individuals and, where relevant, by certification bodies. A generated assessment is input to that judgement, never a substitute for it.
  279. - **`/arckit:atrs` and `/arckit:ai-playbook` do not make an algorithmic tool lawful, fair, or transparent.** An ATRS record is published by the department after its own internal clearance, and the UK Government AI Playbook principles are obligations on the deploying organisation.
  280. - **The EU overlay does not perform conformity assessment.** It drafts documentation referencing the AI Act, NIS2, DORA, CRA, DSA and the Data Act. It is not a notified-body activity, it does not determine your risk classification, and it does not track amendments or implementing acts as they are made.
  281. - **`/arckit:jsp-936` and the NHS clinical safety commands are not assurance either.** Defence AI assurance requires the accountable authority; DCB0129 and DCB0160 require a suitably registered Clinical Safety Officer.
  282. - **No output is a procurement decision.** `/arckit:research` reports evidence. The cloud research, scoring and evaluation commands rank options against stated criteria. The Senior Responsible Owner and the procurement officer decide, under whatever framework rules apply to them.
  283. Two limits apply to everything above:
  284. 1. **Citations reflect the moment they were fetched.** Commands cite sources at fetch time and record the URL, but legislation, standards, framework agreements, and vendor pricing all change. A citation that resolved when the artefact was generated may not describe the current text.
  285. 2. **Generated content can be wrong.** Output is produced by a language model, and research commands extract from third-party web pages that may themselves be inaccurate or written to mislead. ArcKit isolates that extraction behind schema validation and keeps scoring deterministic, which reduces the blast radius but does not make the underlying facts true.
  286. ### Who must review what
  287. Before any ArcKit artefact is relied on, published, or submitted:
  288. - Data protection artefacts (DPIA, records of processing): Data Protection Officer
  289. - Security and assurance artefacts: CISO, or the assessing authority for the relevant regime
  290. - Clinical safety artefacts: a registered Clinical Safety Officer
  291. - Business cases and procurement artefacts: Senior Responsible Owner and procurement or commercial lead
  292. - Anything referencing a regulation, in any jurisdiction: qualified legal counsel for that jurisdiction
  293. The community overlays each carry their own, narrower version of this warning. This section applies to **all** of ArcKit, including the officially-maintained core commands.
  294. ---
  295. ## UK Government Compliance
  296. ArcKit includes dedicated commands for UK public sector delivery:
  297. - `/arckit:tcop` — Assess all 13 Technology Code of Practice points across delivery phases.
  298. - `/arckit:ai-playbook` — Produce responsible AI assessments aligned to the UK Government AI Playbook and ATRS.
  299. - `/arckit:secure` — Generate Secure by Design artefacts covering NCSC CAF, Cyber Essentials, and UK GDPR controls.
  300. - `/arckit:mod-secure` — Map MOD Secure by Design requirements (JSP 440, IAMM, clearance pathways).
  301. - `/arckit:jsp-936` — Deliver JSP 936 AI assurance packs for defence AI systems.
  302. See the demo repositories for end-to-end examples, especially `arckit-test-project-v7-nhs-appointment` (civilian services) and `arckit-test-project-v9-cabinet-office-genai` (AI governance).
  303. ---
  304. ## EU, French, Dutch & Austrian Regulatory Compliance (Community)
  305. > ⚠️ **Community-contributed.** EU and French commands are domain-maintained by [@thomas-jardinet](https://github.com/thomas-jardinet), Austrian commands by [@gtonic](https://github.com/gtonic). The 29 commands below cover EU regulations (GDPR, NIS2, AI Act, DORA, CRA, DSA, Data Act, Cloud Sovereignty Framework), French government standards (SecNumCloud, ANSSI, EBIOS, CNIL, DINUM, etc.), Dutch government standards (Rijksbreed cloudbeleid, VIRBI 2025, BIO2, cloud exit, NORA and GEMMA reference architectures), and Austrian government standards (DSG, NISG 2026, BVergG 2018, BaFG / WZG accessibility). They are not part of the officially-maintained baseline — output should be reviewed by qualified DPO / CISO / Vergabejurist / legal counsel before reliance, and citations may lag current source text. Each command surfaces with a `[COMMUNITY]` prefix in `/help` listings and renders a warning banner before generating.
  306. **EU regulations** (member-state-neutral baselines, applicable across EU/EEA):
  307. - `/arckit:eu-rgpd` — GDPR (EU 2016/679) compliance assessment — legal basis, data subject rights, transfers, DPIA screening, breach notification
  308. - `/arckit:eu-nis2` — NIS2 Directive — operators of essential / important entities, Article 21 measures, incident reporting timelines
  309. - `/arckit:eu-ai-act` — EU AI Act (Regulation 2024/1689) — risk classification (prohibited / high-risk / GPAI), conformity routes
  310. - `/arckit:eu-dora` — Digital Operational Resilience Act (EU 2022/2554) — financial sector ICT risk, TLPT, third-party register
  311. - `/arckit:eu-cra` — Cyber Resilience Act (Regulation 2024/2847) — products with digital elements, SBOM, VDP, CE marking
  312. - `/arckit:eu-cloud-sovereignty` — EU Cloud Sovereignty Framework (v1.2.1, June 2026 calculator weights) — eight weighted sovereignty objectives, SEAL-0 to SEAL-4 assurance levels, minimum-SEAL tender gate
  313. - `/arckit:eu-dsa` — Digital Services Act (Regulation 2022/2065) — intermediaries, platforms, VLOPs, ARCOM
  314. - `/arckit:eu-data-act` — Data Act (Regulation 2023/2854) — connected products, B2B FRAND, cloud switching, Article 32 international governmental access
  315. **French government** (apply on top of the EU baseline for French deployments):
  316. - `/arckit:fr-secnumcloud` — SecNumCloud 3.2 qualification (sovereign cloud, OIV/OSE, extraterritorial risk)
  317. - `/arckit:fr-dinum` — DINUM standards: RGI, RGAA, RGESN, RGS, doctrine cloud de l'État, FranceConnect, DSFR
  318. - `/arckit:fr-marche-public` — French public procurement (code de la commande publique, UGAP, sovereignty clauses)
  319. - `/arckit:fr-rgpd` — CNIL-specific GDPR layer (cookies Délibération 2020-091, HDS, age 15, DPO registration)
  320. - `/arckit:fr-ebios` — EBIOS Risk Manager — 5-workshop study (VM/ER/SR/CO/SS/SO/MS IDs, MITRE ATT&CK, homologation)
  321. - `/arckit:fr-anssi` — ANSSI Guide d'hygiène informatique (42 measures) + cloud security recommendations
  322. - `/arckit:fr-anssi-carto` — ANSSI SI cartography across business / application / system / network levels
  323. - `/arckit:fr-dr` — Diffusion Restreinte handling under II 901 / SGDSN / ANSSI
  324. - `/arckit:fr-algorithme-public` — Public algorithm transparency notice (Article L311-3-1 CRPA, Loi République Numérique)
  325. - `/arckit:fr-pssi` — Information System Security Policy (PSSI) per ANSSI / RGS
  326. - `/arckit:fr-code-reuse` — Public code reuse assessment (code.gouv.fr, SILL, EUPL) — build-vs-reuse decision matrix
  327. **Dutch government** (apply on top of the EU baseline for Netherlands public-sector deployments: central government for the cloud, classification, BIO2 and exit commands, every bestuurslaag for NORA, gemeenten for GEMMA — domain-maintained by [@umag](https://github.com/umag)):
  328. - `/arckit:nl-cloud` — Rijksbreed cloudbeleid 2026 compliance (materieel cloudgebruik, exit plan, CISO Rijk notification, EEA residency, staatsgeheim / TBB eligibility)
  329. - `/arckit:nl-tbb` — Te Beschermen Belangen (TBB) category determination (BIV scoring across five kernbelangen; any existing VIRBI 2025 rubricering is applied as a floor on the category, never derived from it)
  330. - `/arckit:nl-bio` — BIO2 conformance (OBDO, on NEN-EN-ISO/IEC 27001:2023 and 27002:2022)
  331. - `/arckit:nl-exit` — Cloud exit plan under Rijksbreed cloudbeleid clause 3.2 (planned exit and disruptive interruption, annual review)
  332. - `/arckit:nl-nora` — NORA conformance (NAP01–NAP17 per implicatie and Vijflaagsmodel layer, kwaliteitsdoelen and kernwaarden roll-up; GEMMA supplement for gemeenten)
  333. - `/arckit:nl-gemma` — GEMMA landscape mapping for gemeenten (referentiecomponenten, bedrijfsfuncties, overlap, gaps, standards, roadmap candidates)
  334. **Austrian government** (apply on top of the EU baseline for Austrian deployments — domain-maintained by [@gtonic](https://github.com/gtonic)):
  335. - `/arckit:at-dsgvo` — Austrian DSG layer on GDPR (image processing on the GDPR per the VwGH's §12 DSG ruling, ELGA/GTelG health, §96a ArbVG employee monitoring, age 14 consent, DSB enforcement)
  336. - `/arckit:at-nisg` — Austrian NISG 2026 (NIS2 transposition, BGBl. I Nr. 94/2025, in force since 1 Oct 2026) — Essential/Important designation, Cybersicherheitsbehörde registration, CSIRT reporting (CERT.at / GovCERT / HealthCERT), KSÖ, sectoral overlaps (DORA, equivalent sector acts)
  337. - `/arckit:at-bvergg` — Bundesvergabegesetz 2018 procurement — Oberschwellen/Unterschwellen, ANKÖ publication, Bestbieterprinzip, BVwG review
  338. - `/arckit:at-barrierefreiheit` — Digital accessibility across both transposition tracks — BaFG (European Accessibility Act, private sector) and WZG (public sector), EN 301 549 / WCAG 2.1 AA, Barrierefreiheitserklärung, SMS and FFG
  339. These layer cleanly on the existing baseline — `fr-rgpd` / `at-dsgvo` extend `eu-rgpd`, `fr-pssi` / `at-nisg` reference `eu-nis2`, and `fr-secnumcloud` integrates with `arckit.research` and `arckit.evaluate` for procurement workflows. Austrian commands carry `[NEEDS VERIFICATION]` markers where a point is genuinely open rather than unreviewed — further implementing ordinances under the NISG 2026, the applicable Land accessibility laws, current guidance versions, and recent DSB case law. `nl-cloud` and `nl-tbb` play the same role for Dutch deployments, with `nl-cloud` keying its public-cloud eligibility off the TBB category determined by `nl-tbb`.
  340. ---
  341. ## Canada Federal Overlay (12 commands)
  342. Federal Canadian regulatory baseline as a `[COMMUNITY]` overlay — covering FITAA (Bill C-70 2024), federal privacy and access (Privacy Act, ATI Act), Treasury Board Directive on Automated Decision-Making, Charter rights design review, ITSG-33 + Standard on Security Categorization, *Foreign Interference and Security of Information Act* handling, GC Cloud sovereign residency, GC Digital Standards conformance, Official Languages Act, federal procurement (PSPC + PSIB), and First Nations OCAP® data sovereignty.
  343. | Command | Type code | Purpose |
  344. |---|---|---|
  345. | `/arckit:ca-fitaa` | `FITAA` | Foreign Influence Transparency and Accountability Act compliance assessment |
  346. | `/arckit:ca-pia` | `PIA` | Privacy Impact Assessment per Privacy Act + TBS Standard on PIA |
  347. | `/arckit:ca-atip` | `ATIP` | Access to Information / Privacy Act reconciliation and severance design |
  348. | `/arckit:ca-aia` | `AIA` | Algorithmic Impact Assessment per TBS Directive on Automated Decision-Making (Levels I–IV) |
  349. | `/arckit:ca-charter` | `CHRT` | Charter rights design review (s.2 / s.7 / s.8 / s.11 / s.15) with Oakes proportionality |
  350. | `/arckit:ca-itsg-33` | `ITSG` | ITSG-33 Statement of Applicability + Standard on Security Categorization |
  351. | `/arckit:ca-soia` | `SOIA` | *Foreign Interference and Security of Information Act* (formerly the *Security of Information Act*) handling plan for SECRET / TOP SECRET systems |
  352. | `/arckit:ca-cloud-residency` | `CACR` | GC Cloud sovereign residency assessment with CLOUD-Act analysis |
  353. | `/arckit:ca-gc-digital-standards` | `DIGSTD` | Government of Canada Digital Standards conformance scorecard |
  354. | `/arckit:ca-ola` | `OLA` | Official Languages Act review (Parts IV / V / VI) |
  355. | `/arckit:ca-pspc` | `PROC` | Federal procurement strategy (PSPC Supply Manual + PSIB 5%) |
  356. | `/arckit:ca-ocap` | `OCAP` | First Nations OCAP® sovereignty assessment with FNIGC pre-engagement gate |
  357. > **Help wanted**: looking for a Canadian federal enterprise architect to co-maintain this overlay. Open an issue or DM @tractorjuice.
  358. ---
  359. ## UAE Federal Overlay (Community-contributed)
  360. > ⚠️ **Community-contributed overlay.** The 12 commands below cover UAE federal regulatory and digital-government instruments and ship as a **community-contributed overlay** (not part of the officially-maintained baseline of 68). They are anchored on the UAE Cabinet decree of 23 April 2026 mandating that 50% of federal services run on agentic AI by April 2028, and on the federal data, identity, AI governance, and procurement frameworks the decree references. The overlay is currently solo-maintained by @tractorjuice; a UAE domain co-maintainer is being recruited before the overlay can be re-evaluated for official-baseline promotion. Six citations are flagged `[NEEDS VERIFICATION]` pending Executive Regulations and authority confirmations — see [`docs/guides/uae-overlay-maintenance.md`](docs/guides/uae-overlay-maintenance.md). Output should be reviewed by qualified UAE federal compliance counsel before reliance.
  361. Set `governance_framework: UAE Federal` and `classification_scheme: UAE Smart Data` in plugin userConfig to switch the Document Control header into UAE Smart Data classification rendering across every artefact.
  362. **Federal data and security**:
  363. - `/arckit:uae-classification` — UAE Smart Data Classification Register (Open / Confidential / Sensitive / Secret, the four Smart Data Framework classes) with handling rules and declassification schedule
  364. - `/arckit:uae-pdpl` — Federal Decree-Law No. 45 of 2021 (PDPL) compliance assessment — DPIA, lawful-basis register, data-subject-rights procedure, cross-border transfer log
  365. - `/arckit:uae-ias` — UAE Cybersecurity Council Information Assurance Standard v2 — Statement of Applicability against 188 controls (60 management M1–M6, 128 technical T1–T9), priority-tiered P1–P4
  366. - `/arckit:uae-cloud-residency` — National Cloud Security Policy v2 sovereign cloud assessment — per-classification residency, candidate CSPs (Core42 / G42, Microsoft UAE North/Central, TDRA FedNet, e& Sovereign Launchpad on AWS, du Tech National Hypercloud) checked against the policy's tiers and minimum certifications, shared-responsibility matrix, exit/portability plan
  367. **Federal identity**:
  368. - `/arckit:uae-uaepass` — UAE Pass integration design (OIDC/OAuth flow, claim mapping, Basic vs Verified profile selection, Service Provider onboarding, e-signature audit trail)
  369. **Cabinet instruments**:
  370. - `/arckit:uae-zero-bureaucracy` — Service Catalogue review under the UAE Code for Government Services and Zero Bureaucracy programme
  371. - `/arckit:uae-digital-records` — Digital Records Plan under the UAE Government Services Digital Records Policy (source-of-truth register per service, retention schedule, official-source designation)
  372. - `/arckit:uae-data-sharing` — Data Sharing Agreement under the UAE Government Services Data Sharing Policy ("collect once, use securely") with PDPL lawful basis per share
  373. - `/arckit:uae-priorities-alignment` — National Priorities Alignment Statement under the UAE Federal Government Guide — reuse-vs-build, capability-reuse register (UAE Pass, FedNet), strategy alignment to NIS 2031 / AI 2031 / We the UAE 2031
  374. **AI governance**:
  375. - `/arckit:uae-ai-charter` — UAE Charter for the Development and Use of AI compliance assessment (12 principles)
  376. - `/arckit:uae-ai-autonomy-tier` — Three-tier AI autonomy posture (Tier 1 internal-productivity, Tier 2 investor-facing-with-approval, Tier 3 regulated/financial) with per-tier guard-rails, approval gates, audit obligations, tier-promotion criteria
  377. **Procurement**:
  378. - `/arckit:uae-procurement` — Federal procurement strategy under Federal Decree-Law No. 11 of 2023 — ITT/RFP packs against MoF Digital Procurement Platform templates, In-Country Value (ICV) plan, evaluation report structure, contract register
  379. The commands chain together in a canonical order from `principles → uae-classification → uae-pdpl → uae-ias → uae-cloud-residency → uae-uaepass → uae-zero-bureaucracy → uae-digital-records → uae-data-sharing → uae-ai-charter → uae-ai-autonomy-tier → uae-priorities-alignment → uae-procurement → sobc → wardley → framework`. Full guide: [`docs/guides/uae-overlay.md`](docs/guides/uae-overlay.md).
  380. ---
  381. ## UK Legacy IT Assessment Overlay (Community-contributed)
  382. The optional `arckit-uk-legacy` overlay adds one command for existing project systems:
  383. classification against the updated UK definition, independent published numerical risk,
  384. and a finding-linked remediation plan. It bundles the full dated framework material
  385. for offline use and depends on `arckit` core. It does not make LEGACY mandatory for
  386. other projects or approve policy on an owner's behalf.
  387. ```bash
  388. claude plugin install arckit arckit-uk-legacy
  389. ```
  390. | Command | Description | Guide | Status |
  391. |---------|-------------|-------|--------|
  392. | `/arckit-uk-legacy:uk-legacy-assessment` | Assess existing systems and dependencies, calculate independent risk, and plan remediation with evidence and owner review | [Guide](docs/guides/legacy-assessment.md) | Experimental |
  393. ## UK NHS Clinical Safety Overlay (Community-contributed)
  394. > ⚠️ **Community-contributed overlay — second sector-specific overlay in ArcKit, after `arckit-uk-finance`.** The 4 commands below cover NHS clinical safety (DCB0129 manufacturer + DCB0160 deployer), NHS DTAC procurement assurance, and UK MDR 2002 + EU MDR 2017/745 software-as-medical-device classification. Adopts Dr Marcus Baw's [SAFETY.md spec](https://github.com/pacharanero/SAFETY.md) for DCB0129/0160 file naming and YAML-frontmatter hazard log. Output is **not** clinical, legal, or regulatory advice — MUST be reviewed by a qualified Clinical Safety Officer (CSO with appropriate GMC / NMC / HCPC / GPhC registration) and, for MDR classification, by a qualified Regulatory Affairs specialist before reliance.
  395. **Clinical safety (DCB0129 + DCB0160)**:
  396. - `/arckit:uk-nhs-dcb0129` — NHS DCB0129 manufacturer Clinical Safety Case + Hazard Log. Produces a 3-file set in `projects/{NNN}/clinical-safety/`: `SAFETY.md` (front-door anchor), `SAFETY-CASE.md` (GSN-inspired safety argument), `HAZARD-LOG.md` (YAML-frontmatter hazard array + rendered Markdown table; 6 starter hazards covering wrong-patient, stale data, audit, authorisation, alert delivery, write integrity)
  397. - `/arckit:uk-nhs-dcb0160` — NHS DCB0160 deployer Clinical Safety Case + Deployment Hazard Log. Produces a 3-file deployer-side set in `projects/{NNN}/clinical-safety/deployment/`; 10 starter deployment hazards covering training, workflow integration, BC, parallel running, migration, local configuration, terminology, RBAC, incident reporting
  398. **Procurement and regulation**:
  399. - `/arckit:uk-nhs-dtac` — NHS Digital Technology Assessment Criteria, following the DTAC form version 2.0 (24 February 2026; required from 6 April 2026): context sections A and B, assessed sections C1–C4 (Clinical safety, Data protection, Technical security, Interoperability) and scored section D1 (Usability and accessibility), plus an optional AI supplement outside DTAC. Cross-references DCB0129, MDR classification, DPIA, ATRS, Secure by Design
  400. - `/arckit:uk-mdr-classification` — UK MDR 2002 (as amended) + EU MDR 2017/745 software-as-medical-device (SaMD) and AI-as-medical-device (AIaMD) classification. UKCA / UKNI / CE marking pathway, Windsor Framework NI handling, conformity-assessment route, MHRA SaMD/AIaMD Programme alignment, ISO 14971 / IEC 62304 / ISO 13485 standards mapping, post-market obligations
  401. The commands compose with — not replace — the UK government baseline (`tcop`, `secure`, `dpia`, `atrs`, `risk`, `service-assessment`). Recipe: `uk-nhs-clinical-safety` (44 targets across the clinical-safety waves). Proposed domain co-maintainer: Dr Marcus Baw ([@pacharanero](https://github.com/pacharanero)) — clinical informatician at RCPCH, openEHR, NHS England.
  402. The DCB0129/0160 outputs deliberately do **not** carry the `ARC-` prefix — they follow Marcus's SAFETY.md spec convention so they remain readable by clinicians, MHRA reviewers, and procurement teams who do not use ArcKit. Other artefacts cross-reference them by relative path. Full design log (as committed in #501): [`docs/superpowers/specs/2026-05-19-uk-nhs-overlay-design.md`](https://github.com/tractorjuice/arc-kit/blob/469e0b7d/docs/superpowers/specs/2026-05-19-uk-nhs-overlay-design.md).
  403. ---
  404. ## USA Federal Civilian Overlay (10 commands)
  405. > ⚠️ **Community-contributed overlay.** The 10 commands below cover US federal civilian compliance instruments (FedRAMP authorization, FISMA / NIST 800-53 Rev 5, CISA Zero Trust Maturity Model, OMB M-19-17 ICAM, NIST AI RMF + OMB M-25-21/M-25-22 AI assurance, E-Government Act §208 PIA, EO 14028 secure-software evidence and SBOM under OMB M-26-05). They ship as the **arckit-us** community-contributed overlay (not part of the officially-maintained baseline of 72). **EO 14110 was revoked January 2025**; the live AI mandates are **OMB M-25-21** (use of AI; it rescinded and replaced M-24-10 on 3 April 2025) **+ M-25-22** (acquisition of AI; it replaced M-24-18). **FedRAMP completed the Rev 5 transition in 2024**. The overlay is currently solo-maintained by @tractorjuice; a US federal-civilian domain co-maintainer is being recruited (CISO / SAOP / FedRAMP PMO / CAIO backgrounds welcome) before the overlay can be re-evaluated for official-baseline promotion. Output should be reviewed by qualified US federal counsel before reliance.
  406. **In scope (v1)**: federal civilian agencies and the vendors that sell to them.
  407. **Out of scope (sibling overlays for the future)**: federal defense (CMMC / RMF / DISA STIGs), state regimes (StateRAMP / TX-RAMP / CJIS / IRS Pub 1075 / CCPA), sector-specific (HIPAA / GLBA / SOX / FERPA / PCI DSS), Section 508 accessibility (deferred to v5.2).
  408. | Command | Anchor | Doc-type |
  409. |---------|--------|----------|
  410. | `/arckit:us-fisma-categorization` | FIPS Publication 199 + NIST SP 800-60 Vol 2 Rev 1 | `FIPS199` |
  411. | `/arckit:us-nist-800-53` | NIST SP 800-53 Rev 5 + SP 800-53B + FedRAMP Rev 5 baselines | `NIST` |
  412. | `/arckit:us-fedramp-ssp` | FedRAMP SSP Template Rev 5 + NIST SP 800-37 Rev 2 | `FRSSP` |
  413. | `/arckit:us-fedramp-readiness` | FedRAMP 3PAO Readiness Assessment Report template | `FRRR` |
  414. | `/arckit:us-zero-trust` | CISA Zero Trust Maturity Model v2.0 + OMB M-22-09 + NIST SP 800-207 | `ZTA` |
  415. | `/arckit:us-icam` | OMB M-19-17 + NIST SP 800-63-3 (A/B/C) + FIPS 201-3 + login.gov | `ICAM` |
  416. | `/arckit:us-ai-rmf` | NIST AI RMF 1.0 + NIST AI 600-1 (Generative AI Profile) | `AIRMF` |
  417. | `/arckit:us-ai-impact` | OMB M-25-21 + OMB M-25-22 (+ M-26-04 for LLMs) | `AIIA` |
  418. | `/arckit:us-privacy-pia` | E-Government Act §208 + OMB M-03-22 + Privacy Act §552a + NIST SP 800-122 | `USPIA` |
  419. | `/arckit:us-sbom-eo-14028` | EO 14028 + OMB M-26-05 (rescinded M-22-18 / M-23-16) + CISA Secure Software Development Attestation Form (agency choice) + CISA 2026 SBOM Minimum Elements | `SBOM` |
  420. Recipe: `us-federal` (5 waves — baseline → controls → posture → ai → authorization).
  421. Install: `claude plugin install arckit arckit-us`. See [`docs/guides/us-federal-overlay.md`](docs/guides/us-federal-overlay.md) for the USA Federal Civilian overlay maintenance guide and citation register.
  422. ---
  423. ## UK Finance Payments Overlay (4 commands) — First Sector Overlay
  424. > **EXPERIMENTAL sector overlay.** The 4 commands below cover established UK Payment Service Providers, E-Money Institutions and Payment Institutions working under an FCA authorisation: SCA-RTS exemption design, safeguarding under the EMRs 2011, PSRs 2017 and CASS 15, the FCA Consumer Duty board report, and Critical Third Parties dependencies. They ship as the **arckit-uk-finance** community-contributed overlay — the first **sector-specific** overlay (distinct from the 8 jurisdictional overlays). Output requires review by qualified UK FS regulatory counsel, MLRO, and the firm's accountable senior managers (SMF holders only where the firm is within SM&CR) before implementation.
  425. **Payments architecture and compliance**:
  426. - `/arckit:uk-fs-sca-rts` — SCA-RTS exemption design: the ten exemptions in UK SCA-RTS Articles 10 to 18 (FCA technical standards under PSRs 2017 regulation 106A), TRA reference fraud rates and the Article 20 cessation rule, fraud monitoring (FSSCA)
  427. - `/arckit:uk-fs-safeguarding` — EMI / PI safeguarding assessment under EMRs 2011 regulations 20 to 22, PSRs 2017 regulation 23 and CASS 15 (from 7 May 2026), including the monthly safeguarding return; **CRITICAL severity** (FSSAFE)
  428. - `/arckit:uk-fs-consumer-duty` — FCA Consumer Duty annual board report under Principle 12 and PRIN 2A (FSCD)
  429. - `/arckit:uk-fs-ctp-dependency` — Critical Third Parties dependency register and resilience testing plan under PS24/16 and FSMA 2023 (FSCTP)
  430. Recipe: `uk-fs-payments` (11 targets across baseline and overlay commands).
  431. Install: `claude plugin install arckit arckit-uk-finance`. Help wanted: recruiting a UK financial services domain co-maintainer (CISO / Compliance / Head of Architecture background welcome) to transition to official-baseline status.
  432. ---
  433. ## UK G-Cloud Supplier Bid-Authoring Overlay (15 commands) — Proprietary
  434. > **PROPRIETARY, Claude Code only.** The 15 commands below are a supplier-side overlay for authoring UK G-Cloud 15 (RM1557.15) Digital Marketplace bids, run by the Government Commercial Agency (GCA, formerly CCS): supplier profile, social value, lot questions, the Procurement Act 2023 supplier declaration, service design, a Service Definition Document for each of the five lots (1a, 1b, 2a, 2b, 3), pricing, security evidence, competitor benchmarking, submission review, and a final submission pack. Unlike the MIT-licensed core, `arckit-uk-gcloud` ships under a **proprietary licence (not MIT)** and is **not distributed to the non-Claude extension formats** (Codex / Gemini / OpenCode / Copilot) — it runs on Claude Code only. It is the 4th sector-specific overlay (after `arckit-uk-finance`, `arckit-uk-nhs`, `arckit-au-energy`) and requires the `arckit` core plugin.
  435. **Supplier-wide (once per bid)**:
  436. - `/arckit:supplier-profile` — Supplier profile: company, CDP and PPON, contacts, certifications, insurance (SUPP)
  437. - `/arckit:social-value` — Social value commitments, Social Value Contact and operational readiness, 10% pass/fail on every lot (SOCV)
  438. - `/arckit:lot-questions` — Lot questions per lot group: conditions of participation, scored Lot 1a/1b quality answers, Lot 2 and Lot 3 mandatory award criteria (LOTQ)
  439. - `/arckit:declaration` — Procurement Act 2023 supplier declaration (DECL)
  440. **Per service**:
  441. - `/arckit:service-design` — Service design, lot choice and value proposition (SVCD)
  442. - `/arckit:sdd-lot1a` — Service Definition Document, Lot 1a IaaS and PaaS (SDD)
  443. - `/arckit:sdd-lot1b` — Service Definition Document, Lot 1b IaaS and PaaS above OFFICIAL (SDD)
  444. - `/arckit:sdd-lot2a` — Service Definition Document, Lot 2a Infrastructure Software as a Service (SDD)
  445. - `/arckit:sdd-lot2b` — Service Definition Document, Lot 2b Software as a Service (SDD)
  446. - `/arckit:sdd-lot3` — Service Definition Document, Lot 3 Cloud Support, with the DDaT role levels that deliver it (SDD)
  447. - `/arckit:pricing` — Pricing by lot: 1a/1b price formula, 2a/2b discount bands; for Lot 3, the supplier's one DDaT rate card, shared by every Lot 3 service (PRIC, RATE)
  448. - `/arckit:security` — Security evidence: certifications by lot and the NCSC Cloud Security Principles (SECA)
  449. - `/arckit:gcloud-competitors` — G-Cloud competitor benchmark (GCMP)
  450. - `/arckit:review` — G-Cloud submission review and gap analysis (GCRV)
  451. - `/arckit:submission-pack` — Assemble the final G-Cloud submission pack
  452. Recommended order: supplier-profile → social-value → service-design → the lot's SDD command → pricing and security → lot-questions → declaration → review → submission-pack. The lot questions come after the SDDs because their award criteria repeat each service's answers.
  453. Skills: `gcloud-framework` (G-Cloud 15 question set, limits and evaluation), `cloud-security`, `ddat-rate-card` (Lot 3 job families, roles and levels; replaces `sfia-skills`). Recipe: `uk-gcloud-submission` (end-to-end bid assembly). G-Cloud 14 is no longer supported: `/arckit:sdd-lot1` is replaced by `sdd-lot1a` and `sdd-lot1b`, and `/arckit:sdd-lot2` by `sdd-lot2a` and `sdd-lot2b`.
  454. Install: `claude plugin install arckit arckit-uk-gcloud`. Proprietary — see the licence-exception note at the foot of this README. Ported from the standalone gcloud-kit plugin.
  455. ---
  456. ## TOGAF ADM Overlay (`arckit-togaf-adm`) [COMMUNITY]
  457. Enterprise Architecture Development Method — 9 commands covering the full ADM cycle.
  458. | Command | Doc Type | Phase | Description |
  459. |---------|----------|-------|-------------|
  460. | `/arckit:adm-preliminary` | ADMP | Preliminary | Architecture vision, scope, drivers, constraints |
  461. | `/arckit:business-capability-map` | BPCM | Phase B | Business capability hierarchy, value streams, maturity |
  462. | `/arckit:application-inventory` | APP | Phase C | Application catalog with strategic fit scoring |
  463. | `/arckit:application-rationalization` | APPR | Phase C | Keep/merge/replace/retire decisions |
  464. | `/arckit:gap-analysis` | GAPA | Phase E | Capability gap matrix, workstream mapping |
  465. | `/arckit:transition-architecture` | TRANS | Phase F | Work packages, migration waves, acceptance criteria |
  466. | `/arckit:architecture-board` | BORD | Phase G | Board charter, compliance scorecard, governance |
  467. | `/arckit:architecture-change` | ACHG | Phase H | Change requests, ADM cycle re-entry |
  468. | `/arckit:architecture-repository` | REPO | Repository | Patterns, standards, reference architectures |
  469. **Install:** `claude plugin install arckit arckit-togaf-adm`
  470. **Recipe:** `togaf-adm-full` — full ADM cycle via build recipe
  471. ---
  472. ## O-AA Overlay (`arckit-oaa`) [COMMUNITY]
  473. Open Agile Architecture (O-AA Standard, Version 2.0, C262) — agile enterprise architecture for product-driven, sprint-based delivery. A standalone overlay alongside `arckit-togaf-adm`; the two are complementary, not competitors — see the [O-AA vs TOGAF ADM decision guide](plugins/arckit-oaa/README.md#oaa-vs-togaf-adm).
  474. | Command | Doc Type | Description |
  475. |---------|----------|-------------|
  476. | `/arckit-oaa:oaa-adm-lite` | `OAAL` | Maps TOGAF ADM cycle to agile sprints (4–8 week engagement windows) |
  477. | `/arckit-oaa:product-architecture` | `OAPR` | Product-centric architecture — cross-functional teams, backlog-driven delivery |
  478. | `/arckit-oaa:agile-strategy` | `OASTR` | Dual transformation canvas — digital transformation + agile transformation |
  479. | `/arckit-oaa:agile-security` | `OASEC` | Security embedded in sprint rhythm — threat modeling, compliance evidence |
  480. | `/arckit-oaa:agile-governance` | `OAGOV` | Lightweight governance cadence aligned to sprint cycles |
  481. Handoff chain: `oaa-adm-lite` → `product-architecture` → `agile-strategy` → `agile-security` → `agile-governance`.
  482. **Install:** `claude plugin install arckit arckit-oaa`
  483. **Recipe:** `oaa-full` — ADM Lite → product → strategy → security → governance
  484. ---
  485. ## Using TOGAF ADM and O-AA Together
  486. The two overlays are **complementary, not competitors**. Each depends only on the `arckit` core (`=6.22.1` pin) — neither depends on the other. O-AA maps the ADM cycle onto sprints within a 4–8 week engagement; `arckit-togaf-adm` keeps the full document-centric ADM. Decision guide: [O-AA vs TOGAF ADM](plugins/arckit-oaa/README.md#oaa-vs-togaf-adm).
  487. | Pattern | When to use | Sequence |
  488. |---------|-------------|----------|
  489. | **A — Baseline, then sprints** (recommended when both apply) | Regulatory audit trail *and* sprint delivery | TOGAF `togaf-adm-full` → O-AA `oaa-full` on the same project |
  490. | **B — O-AA only** | Hard deadline < 8 weeks, agile culture, product-centric; no enterprise baseline needed | O-AA `oaa-full` (foundation targets come from core) |
  491. | **C — TOGAF ADM only** | Full regulatory audit, 50+ stakeholder gates, quarterly architecture boards | TOGAF `togaf-adm-full` |
  492. **Install for pattern A** (one plugin per CLI invocation; community plugins install disabled):
  493. ```bash
  494. claude plugin install arckit
  495. claude plugin install arckit-togaf-adm && claude plugin enable arckit-togaf-adm
  496. claude plugin install arckit-oaa && claude plugin enable arckit-oaa
  497. ```
  498. **Running both in the same project:**
  499. - No collisions: separate namespaces (`/arckit-togaf-adm:` vs `/arckit-oaa:`) and doc-type codes; one core install satisfies both `=6.22.1` pins.
  500. - No schema files are shared between the overlays. The O-AA YAML sprint artefacts are defined in the O-AA templates and kept consistent with the matching TOGAF documents: `vision.yaml` with the ADM Preliminary, which `oaa-adm-lite` reads, and `implementation-strategy.yaml` with the transition architecture. `oaa-adm-lite` sends Sprint 4+ architecture change requests through `/arckit-togaf-adm:architecture-change`. `agile-governance` defines its own `change-request.yaml` and `compliance-evidence.yaml` (the latter shared with `agile-security`) and does not read `architecture-change` output.
  501. - Order: run the TOGAF baseline first, then let O-AA sprints execute it at sprint velocity. O-AA commands read TOGAF outputs when they exist (ADM Preliminary, business capability map, transition architecture) but do not require them, so the reverse order works mechanically — you just lose the "sprints execute the baseline" benefit.
  502. ---
  503. ## arc42 Overlay (`arckit-arc42`) [COMMUNITY]
  504. Writes an [arc42](https://arc42.org) architecture description for one system, assembled from the artefacts the project already has, and hands it over to a Specification Driven Development tool. arc42 is a documentation structure rather than a method, so the overlay has one assembly command: each of the 12 sections summarises and cites its source artefacts, and sections no artefact covers are listed in a Gap Register with the command that would fill them. Four source commands write the artefacts three sections need and core does not produce, and the handover pack carries requirement and decision IDs into [Spec Kit](https://github.com/github/spec-kit).
  505. | Command | Doc Type | Description |
  506. |---------|----------|-------------|
  507. | `/arckit-arc42:arc42` | `ARC42` | All 12 arc42 sections from existing artefacts, each cited, with a Gap Register and a Source Artefacts table |
  508. | `/arckit-arc42:arc42-quality` | `QUAL` | Quality tree and measurable quality scenarios for section 10, classified by the nine Q42 dimensions; goals without a measurable target listed, never estimated |
  509. | `/arckit-arc42:arc42-concepts` | `CONC` | Crosscutting concepts for section 8, each traced to the ADR or design that settles it; open concepts routed to ADRs |
  510. | `/arckit-arc42:arc42-debt` | `DEBT` | Technical debt register for section 11.2, consolidated from audits, conformance assessments, reviews, ADRs and risks |
  511. | `/arckit-arc42:arc42-handover` | `SDDH` | SDD handover pack for Spec Kit: constitution, one feature brief per epic and plan inputs, tagged with ArcKit IDs |
  512. **Install:** `claude plugin install arckit arckit-arc42`
  513. **Recipe:** `arc42-full` — principles → stakeholders → requirements → ADRs and data model → context, container, runtime and deployment diagrams → Secure by Design → risks → glossary → quality scenarios → crosscutting concepts → arc42 (`--enable DEBT` and `--enable SDDH` add the debt register and handover pack)
  514. The adapted arc42 template and its copies are CC BY-SA 4.0, based on [arc42](https://arc42.org/license/) by Peter Hruschka and Gernot Starke. The quality template and the `arc42-quality` command's Q42 classification are CC BY-SA 4.0 as well, adapted from the [Q42 quality model](https://quality.arc42.org) by Gernot Starke. The notice records ArcKit's changes; original command logic, recipes, scripts and the concepts, debt and handover templates remain MIT-licensed. See the [third-party notice](plugins/arckit-arc42/templates/arc42-LICENSE.md).
  515. ---
  516. ## AI Agent Architecture Overlay (`arckit-agent-architecture`) [COMMUNITY]
  517. Governance, design, and security for autonomous AI agent programs — 6 commands.
  518. | Command | Doc Type | Description |
  519. |---------|----------|-------------|
  520. | `/arckit:agent-inventory` | AAGI | Agent catalog with capabilities, security classification |
  521. | `/arckit:agent-design` | AAGR | Agent architecture spec — patterns, tools, memory, orchestration |
  522. | `/arckit:agent-governance` | AAOV | Oversight models, approval workflows, audit, compliance |
  523. | `/arckit:agent-integration` | AAIN | Multi-agent orchestration, contracts, shared state |
  524. | `/arckit:agent-security` | AASE | Sandboxing, permissions, injection defences, output validation |
  525. | `/arckit:agent-maturity` | AAMT | 5×5 maturity model for agent programs |
  526. **Install:** `claude plugin install arckit arckit-agent-architecture`
  527. **Recipe:** `agent-architecture` — full agent architecture lifecycle via build recipe
  528. ### Combined Recipe: `togaf-agent-full`
  529. For organisations adopting both enterprise architecture and AI agent governance:
  530. ```bash
  531. claude agent recipes/togaf-agent-full.yaml
  532. ```
  533. ---
  534. ## The ArcKit Workflow
  535. ArcKit guides you through the enterprise architecture lifecycle:
  536. ### Phase 0: Project Planning
  537. **`/arckit:plan`** → Create project plan with timeline, phases, and gates
  538. Visualize your entire project delivery:
  539. - GDS Agile Delivery phases (Discovery → Alpha → Beta → Live)
  540. - Mermaid Gantt chart with timeline, dependencies, and milestones
  541. - Workflow diagram showing gates and decision points
  542. - Tailored timeline based on project complexity
  543. - Integration of all ArcKit commands into schedule
  544. - Gate approval criteria for governance
  545. ### Phase 1: Establish Governance
  546. **`/arckit:principles`** → Create enterprise architecture principles
  547. Define your organisation's architecture standards:
  548. - Cloud strategy (AWS/Azure/GCP)
  549. - Security frameworks (Zero Trust, compliance)
  550. - Technology standards
  551. - FinOps and cost governance
  552. ### Phase 2: Stakeholder Analysis
  553. **`/arckit:stakeholders`** → Analyze stakeholder drivers, goals, and outcomes
  554. **Do this BEFORE business case** to understand who cares about the project and why:
  555. - Identify all stakeholders (internal and external)
  556. - Document underlying drivers (strategic, operational, financial, compliance, risk, personal)
  557. - Map drivers to SMART goals
  558. - Map goals to measurable outcomes
  559. - Create Stakeholder → Driver → Goal → Outcome traceability
  560. - Identify conflicts and synergies
  561. - Define engagement and communication strategies
  562. ### Phase 3: Risk Assessment
  563. **`/arckit:risk`** → Create comprehensive risk register (Orange Book)
  564. **Do this BEFORE business case** to identify and assess risks systematically:
  565. - Follow HM Treasury Orange Book 2023 framework
  566. - Identify risks across 6 categories (Strategic, Operational, Financial, Compliance, Reputational, Technology)
  567. - Assess inherent risk (before controls) and residual risk (after controls)
  568. - Apply 4Ts response framework (Tolerate, Treat, Transfer, Terminate)
  569. - Link every risk to stakeholder from RACI matrix
  570. - Monitor risk appetite compliance
  571. - Feed into SOBC Management Case Part E
  572. ### Phase 4: Business Case Justification
  573. **`/arckit:sobc`** → Create Strategic Outline Business Case (SOBC)
  574. **Do this BEFORE requirements** to justify investment and secure approval:
  575. - Use HM Treasury Green Book 5-case model (Strategic, Economic, Commercial, Financial, Management)
  576. - Analyze strategic options (Do Nothing, Minimal, Balanced, Comprehensive)
  577. - Map benefits to stakeholder goals (complete traceability)
  578. - Provide high-level cost estimates (Rough Order of Magnitude)
  579. - Economic appraisal (ROI range, payback period)
  580. - Procurement and funding strategy
  581. - Governance and risk management (uses risk register)
  582. - Enable go/no-go decision BEFORE detailed requirements work
  583. ### Phase 5: Define Requirements
  584. **`/arckit:requirements`** → Document comprehensive requirements
  585. Create detailed requirements **informed by stakeholder goals** (if SOBC approved):
  586. - Business requirements with rationale
  587. - Functional requirements with acceptance criteria
  588. - Non-functional requirements (performance, security, scalability, compliance)
  589. - Integration requirements (upstream/downstream systems)
  590. - Data requirements (DR-xxx)
  591. - Success criteria and KPIs
  592. ### Phase 5.3: Platform Strategy Design (Optional - for Multi-Sided Platforms)
  593. **`/arckit:platform-design`** → Design multi-sided platform strategy using Platform Design Toolkit
  594. Use this phase when designing **ecosystem-based platforms** (Government as a Platform, marketplaces, data platforms):
  595. - **Ecosystem Canvas**: Map supply side, demand side, supporting entities with relationship diagrams
  596. - **Entity-Role Portraits**: Deep dive into 3-5 key entities (context, pressures, goals, gains)
  597. - **Motivations Matrix**: Identify synergies and conflicts across entities with mitigation strategies
  598. - **Transactions Board**: Design 10-20 transactions with cost reduction analysis (search, information, negotiation, coordination, enforcement)
  599. - **Learning Engine Canvas**: 5+ services that help participants improve (data, feedback loops, network effects)
  600. - **Platform Experience Canvas**: Journey maps with business model and unit economics
  601. - **MVP Canvas**: Liquidity bootstrapping strategy to solve chicken-and-egg problem
  602. - **Platform Design Canvas**: Synthesize all 8 canvases into cohesive platform strategy
  603. - **UK Government Context**: Aligns with Government as a Platform (GaaP), TCoP Point 8 (share/reuse), Digital Marketplace
  604. **Use Cases**: NHS appointment booking, local authority data marketplaces, training procurement platforms, citizen services portals
  605. ### Phase 5.5: Data Modeling
  606. **`/arckit:data-model`** → Create comprehensive data model with ERD
  607. Create data model based on Data Requirements (DR-xxx):
  608. - Visual Entity-Relationship Diagram (ERD) using Mermaid
  609. - Detailed entity catalog with attributes, types, validation rules
  610. - PII identification and GDPR/DPA 2018 compliance
  611. - Data governance matrix (business owners, stewards, custodians)
  612. - CRUD matrix showing component access patterns
  613. - Data integration mapping (upstream sources, downstream consumers)
  614. - Data quality framework with measurable metrics
  615. - Requirements traceability (DR-xxx → Entity → Attribute)
  616. ### Phase 5.7: Data Protection Impact Assessment
  617. **`/arckit:dpia`** → Generate [DPIA](https://ico.org.uk/for-organisations/uk-gdpr-guidance-and-resources/accountability-and-governance/data-protection-impact-assessments-dpias/) for UK GDPR Article 35 compliance
  618. **MANDATORY for high-risk processing** - assess privacy risks before technology selection:
  619. - ICO 9-criteria automated screening (sensitive data, large scale, vulnerable subjects, AI/ML, etc.)
  620. - Auto-populated from data model (entities, PII, special category data, lawful basis)
  621. - Risk assessment focused on impact on individuals (privacy harm, discrimination)
  622. - Data subject rights implementation checklist (SAR, deletion, portability)
  623. - Children's data assessment (age verification, parental consent)
  624. - AI/ML algorithmic processing assessment (bias, explainability, human oversight)
  625. - ICO prior consultation flagging for high residual risks
  626. - International transfer safeguards (SCCs, BCRs, adequacy decisions)
  627. - Bidirectional links to risk register (DPIA-xxx risk IDs)
  628. - Links mitigations to Secure by Design security controls
  629. ### Phase 5.8: Data Source Discovery
  630. **`/arckit:datascout`** → Discover external data sources
  631. Discover and evaluate external data sources to fulfil project data requirements:
  632. - Data needs extraction from DR/FR/INT/NFR requirements
  633. - UK Government open data portals (data.gov.uk, ONS, NHS Digital, Companies House, OS Data Hub)
  634. - Commercial API providers and data marketplaces
  635. - Free/freemium APIs and open source datasets
  636. - Weighted evaluation scoring (Requirements Fit, Data Quality, License & Cost, API Quality, Compliance, Reliability)
  637. - Gap analysis for unmet data needs
  638. - Data model impact assessment (new entities, attributes, sync strategy)
  639. - Requirements traceability (every DR-xxx mapped to a source or flagged as gap)
  640. - TCoP Point 10 compliance (Make Better Use of Data)
  641. ### Phase 6: Technology Research
  642. **`/arckit:research`** → Research technology, services, and products
  643. Research the solutions available to meet requirements, with checked facts and published costs. It makes no build-or-buy decision: `/arckit:wardley` decides sourcing and `/arckit:sobc` appraises value for money.
  644. - Dynamic category detection from requirements (authentication, payments, databases, etc.)
  645. - Commercial SaaS options with pricing, reviews, and ratings (WebSearch)
  646. - Open source alternatives with GitHub stats and community maturity
  647. - UK Government GOV.UK platforms (One Login, Pay, Notify, Forms)
  648. - Digital Marketplace suppliers (G-Cloud, DOS)
  649. - Published 3-year costs, including supplier price documents on G-Cloud
  650. - What each option meets and lacks against the requirements, all cited
  651. - Market evidence for Wardley mapping (how many products cover each capability)
  652. - Feeds into SOBC Economic Case (cost data)
  653. ### Phase 6.5: Grants & Funding Research
  654. **`/arckit:grants`** → Research UK government grants, charitable funding, and accelerator programmes
  655. Identify and evaluate funding opportunities with eligibility scoring:
  656. - UK Innovate UK grants and R&D funding (e.g. Knowledge Transfer Partnerships, SBRI)
  657. - UK Research and Innovation (UKRI) funding calls
  658. - Charitable foundations and philanthropic funding (e.g. National Lottery Heritage Fund, Wellcome Trust)
  659. - Accelerator and incubator programmes (e.g. DCMS, DSIT-backed cohorts)
  660. - EU Horizon Europe successor funding open to UK entities
  661. - Eligibility scoring matrix against project requirements and stakeholder profile
  662. - Application timeline, deadlines, and award values
  663. - Strategic fit assessment (alignment with project goals and public sector context)
  664. - Outputs a structured GRNT funding opportunity register
  665. ### Phase 7: Strategic Planning with Wardley Mapping
  666. **`/arckit:wardley`** → Create strategic Wardley Maps
  667. Visualize strategic positioning with:
  668. - Component evolution analysis (Genesis → Custom → Product → Commodity)
  669. - Build vs Buy decision framework
  670. - Vendor comparison and procurement strategy
  671. - UK Government Digital Marketplace mapping
  672. - Evolution predictions and strategic gameplay
  673. ### Phase 7.5: Strategic Roadmap
  674. **`/arckit:roadmap`** → Create multi-year architecture roadmap
  675. Create strategic roadmap for multi-year transformation programs:
  676. - **Multi-year timeline**: 3-5 year roadmap with Mermaid Gantt chart aligned to financial years (FY 2024/25, etc.)
  677. - **Strategic themes**: Cloud migration, data modernization, security & compliance, DevOps transformation
  678. - **Capability evolution**: Maturity progression from L1 (Initial) to L5 (Optimized) over time
  679. - **Investment planning**: CAPEX/OPEX budget by financial year, ROI projections, benefits realization
  680. - **Governance framework**: ARB monthly, Programme Board monthly, Steering Committee quarterly
  681. - **Service Standard gates**: Alpha/Beta/Live assessment milestones (UK Government)
  682. - **Dependencies**: Mermaid flowchart showing initiative sequencing and critical path
  683. - **Success metrics**: Cloud adoption %, technical debt reduction, deployment frequency, time to market
  684. - **Traceability**: Links roadmap themes to stakeholder drivers, architecture principles, requirements
  685. - **UK Government specifics**: Spending Review alignment, TCoP compliance timeline, NCSC CAF progression
  686. **Use this when**: You have a multi-year transformation program with multiple initiatives running in parallel. Roadmaps are strategic (multi-year, multi-initiative, executive communication) vs project plans which are tactical (single initiative, detailed tasks, team execution).
  687. **Roadmap feeds into**: `/arckit:plan` for detailed phase execution, `/arckit:sobc` for investment business case, `/arckit:backlog` for prioritized user stories, `/arckit:strategy` for executive-level synthesis.
  688. ### Phase 7.6: Architecture Strategy Synthesis
  689. **`/arckit:strategy`** → Synthesise strategic artifacts into executive-level Architecture Strategy
  690. Create a comprehensive Architecture Strategy document that synthesises multiple strategic artifacts into a single coherent narrative:
  691. - **Strategic vision**: 2-3 paragraphs articulating the transformation vision and success definition
  692. - **Strategic drivers**: Summarised from stakeholder analysis with external drivers (regulatory, market, technology)
  693. - **Guiding principles**: Key principles with strategic implications, compliance summary
  694. - **Current state assessment**: Technology landscape, capability maturity baseline (L1-L5), technical debt, SWOT
  695. - **Target state vision**: Future architecture, capability maturity targets, architecture vision diagram
  696. - **Technology evolution**: Build vs buy decisions, technology radar (Adopt/Trial/Assess/Hold) from Wardley maps
  697. - **Strategic themes**: 3-5 investment themes with objectives, initiatives, success criteria, principles alignment
  698. - **Delivery roadmap summary**: Timeline, phases, milestones from roadmap artifact
  699. - **Investment summary**: CAPEX/OPEX, NPV, IRR, payback period, benefits realisation from SOBC
  700. - **Strategic risks**: Top risks with heat map, assumptions, constraints from risk register
  701. - **Success metrics**: KPIs with baselines and year-over-year targets
  702. - **Governance model**: Forums, decision rights, review cadence
  703. - **Traceability**: Driver → Goal → Outcome → Theme → Principle → KPI chain
  704. **Use this when**: You have multiple strategic artifacts (principles, stakeholders, wardley, roadmap, sobc) and need to create a single executive-level document that synthesises them into a coherent strategy. Ideal for Strategy Board presentations, executive briefings, or stakeholder communication.
  705. **Unique requirement**: This is the only ArcKit command with TWO mandatory inputs (principles AND stakeholders). Strategy cannot be created without understanding both the decision framework and the stakeholder drivers.
  706. **Strategy feeds into**: `/arckit:requirements` for detailed requirements, `/arckit:roadmap` for expanded timeline, `/arckit:plan` for project delivery.
  707. ### Phase 7.7: Architecture Decision Records
  708. **`/arckit:adr`** → Document architectural decisions
  709. Create Architecture Decision Records (ADRs) following MADR v4.0 format enhanced with UK Government requirements:
  710. - **Decision metadata**: Sequential numbering (ADR-001, ADR-002), status (Proposed/Accepted/Superseded), escalation level (Team/Cross-team/Department/Cross-government)
  711. - **Stakeholder RACI**: Deciders (accountable), Consulted (SMEs, two-way), Informed (one-way communication)
  712. - **Context and problem statement**: Why this decision is needed, business/technical/regulatory drivers
  713. - **Decision drivers**: Technical forces (performance, security, scalability), business forces (cost, time), compliance forces (GDS Service Standard, TCoP, NCSC, UK GDPR)
  714. - **Options analysis**: Minimum 2-3 options plus "Do Nothing" baseline, each with pros/cons, cost (CAPEX/OPEX/TCO), GDS Service Standard impact, Wardley evolution stage
  715. - **Y-Statement**: Structured justification - "In the context of X, facing Y, we decided for Z to achieve A, accepting B"
  716. - **Consequences**: Positive (benefits, capabilities), Negative (trade-offs, technical debt), Neutral (training, infrastructure), Risks and mitigations
  717. - **Validation**: How implementation will be verified (design reviews, code reviews, testing, monitoring)
  718. - **Traceability**: Links to requirements, principles, stakeholders, research, Wardley maps, diagrams, risk register
  719. - **UK Government specifics**: Escalation levels (Team → Cross-team → Department → Cross-government), governance forums (ARB, TDA, Programme Board), Service Standard/TCoP compliance documentation
  720. **Use this when**: Making significant architectural decisions that affect system structure, quality attributes, or behavior - technology choices (databases, frameworks, cloud services), integration patterns, security approaches, deployment strategies, data management.
  721. **ADR feeds into**: `/arckit:diagram` (architecture diagrams reflect decisions), `/arckit:hld-review` and `/arckit:dld-review` (reviews verify decisions implemented), `/arckit:traceability` (decisions are key traceability artifacts).
  722. ### Phase 8: Vendor Procurement (if needed)
  723. **`/arckit:sow`** → Generate Statement of Work (RFP)
  724. Create RFP-ready documents with:
  725. - Scope of work and deliverables
  726. - Technical requirements
  727. - Vendor qualifications
  728. - Evaluation criteria
  729. - Contract terms
  730. **`/arckit:dos`** → Digital Outcomes and Specialists (DOS) procurement 🇬🇧
  731. For UK public sector organizations needing custom development:
  732. - Generate DOS-compliant procurement documentation
  733. - Extract requirements from project artifacts (BR/FR/NFR/INT/DR)
  734. - Essential vs desirable skills from requirements
  735. - Success criteria (technology-agnostic)
  736. - Evaluation framework (40% Technical, 30% Team, 20% Quality, 10% Value)
  737. - Audit-ready documentation for Digital Marketplace
  738. **`/arckit:gcloud-search`** → G-Cloud service search with live marketplace search 🇬🇧
  739. For UK public sector organizations needing off-the-shelf cloud services:
  740. - Generate G-Cloud requirements document
  741. - **Live Digital Marketplace search** using WebSearch
  742. - Find actual services with suppliers, prices, features, links
  743. - Service comparison table with recommendations
  744. - Shortlist top 3-5 matching services
  745. - Links to Digital Marketplace guidance (gov.uk)
  746. **`/arckit:gcloud-clarify`** → G-Cloud service validation and gap analysis 🇬🇧
  747. Validate G-Cloud services and generate supplier clarification questions:
  748. - **Systematic gap analysis** (MUST/SHOULD requirements vs service descriptions)
  749. - Detect gaps: ✅ Confirmed, ⚠️ Ambiguous, ❌ Not mentioned
  750. - Generate prioritised questions (🔴 Critical / 🟠 High / 🔵 Medium / 🟢 Low)
  751. - Risk assessment matrix for each service
  752. - Email templates for supplier engagement
  753. - Evidence requirements specification
  754. - Next steps checklist
  755. **`/arckit:evaluate`** → Create vendor evaluation framework
  756. Set up systematic scoring:
  757. - Technical evaluation criteria (100 points)
  758. - Cost evaluation methodology
  759. - Reference check templates
  760. - Decision matrix
  761. **`/arckit:evaluate`** (compare mode) → Compare vendor proposals
  762. Side-by-side analysis of:
  763. - Technical approaches
  764. - Cost breakdowns
  765. - Risk assessments
  766. - Value propositions
  767. ### Phase 9: Design Review
  768. **`/arckit:hld-review`** → Review High-Level Design
  769. Validate designs against:
  770. - Architecture principles compliance
  771. - Requirements coverage
  772. - Security and compliance
  773. - Scalability and resilience
  774. - Operational readiness
  775. **`/arckit:dld-review`** → Review Detailed Design
  776. Implementation-ready validation:
  777. - Component specifications
  778. - API contracts (OpenAPI)
  779. - Database schemas
  780. - Security implementation
  781. - Test strategy
  782. ### Phase 10: Sprint Planning
  783. **`/arckit:backlog`** → Generate prioritised product backlog
  784. Transform requirements into sprint-ready user stories:
  785. - Convert requirements (BR/FR/NFR/INT/DR) to GDS-format user stories
  786. - Multi-factor prioritization (MoSCoW + risk + value + dependencies)
  787. - Organise into sprint plan with capacity balancing
  788. - Generate traceability matrix (requirements → stories → sprints)
  789. - Export to Jira/Azure DevOps (CSV) or custom tools (JSON)
  790. - **Time savings**: 75%+ (4-6 weeks → 3-5 days)
  791. **When to run**: After HLD approval, before Sprint 1 (Alpha → Beta transition)
  792. ### Phase 10.5: Backlog Export
  793. **`/arckit:trello`** → Export product backlog to Trello
  794. Push your backlog directly to Trello for sprint execution:
  795. - Create Trello board with sprint-based lists (Product Backlog + per-sprint + In Progress + Done)
  796. - Cards with priority labels, story points, and acceptance criteria checklists
  797. - Colour-coded labels by MoSCoW priority and requirement type
  798. - Rate-limit-aware Trello API integration
  799. - Requires `TRELLO_API_KEY` and `TRELLO_TOKEN` environment variables
  800. **When to run**: After `/arckit:backlog` generates the product backlog (requires JSON export)
  801. ### Phase 11: ServiceNow Service Management Design
  802. **`/arckit:servicenow`** → Generate ServiceNow service design
  803. Bridge architecture to operations:
  804. - CMDB design (derived from architecture diagrams)
  805. - SLA definitions (derived from NFRs)
  806. - Incident management design
  807. - Change management plan
  808. - Monitoring and alerting plan
  809. - Service transition plan
  810. ### Phase 12: Traceability
  811. **`/arckit:traceability`** → Generate traceability matrix
  812. Ensure complete coverage:
  813. - Requirements → Design mapping
  814. - Design → Test mapping
  815. - Gap analysis and orphan detection
  816. - Change impact tracking
  817. ### Phase 13: Quality Assurance
  818. **`/arckit:analyze`** → Comprehensive governance quality analysis
  819. Periodically assess governance quality across all artifacts:
  820. - Architecture principles compliance
  821. - Requirements coverage and traceability
  822. - Stakeholder alignment verification
  823. - Risk management completeness
  824. - Design review quality
  825. - Documentation completeness and quality
  826. - Gap identification and recommendations
  827. **When to use**: Run periodically (before milestones, design reviews, or procurement decisions) to identify gaps and ensure governance standards are maintained.
  828. ### Phase 14: Compliance Assessment (UK Government)
  829. For UK Government and public sector projects:
  830. **`/arckit:service-assessment`** → [GDS Service Standard](https://www.gov.uk/service-manual/service-assessments) assessment preparation
  831. Prepare for mandatory GDS Service Standard assessments:
  832. - Analyze evidence against all 14 Service Standard points
  833. - Identify gaps for alpha, beta, or live assessments
  834. - Generate RAG (Red/Amber/Green) ratings and overall readiness score
  835. - Provide actionable recommendations with priorities and timelines
  836. - Include assessment day preparation guidance
  837. - Map ArcKit artifacts to Service Standard evidence requirements
  838. Run at end of Discovery (for alpha prep), mid-Beta (for beta prep), or before Live to ensure readiness.
  839. **`/arckit:tcop`** → [Technology Code of Practice](https://www.gov.uk/guidance/the-technology-code-of-practice) assessment
  840. Assess compliance with all 13 TCoP points:
  841. - Point 1: Define user needs
  842. - Point 2: Make things accessible
  843. - Point 3: Be open and use open source
  844. - Point 4: Make use of open standards
  845. - Point 5: Use cloud first
  846. - Point 6: Make things secure
  847. - Point 7: Make privacy integral
  848. - Point 8: Share, reuse and collaborate
  849. - Point 9: Integrate and adapt technology
  850. - Point 10: Make better use of data
  851. - Point 11: Define your purchasing strategy
  852. - Point 12: Meet the Digital Spend Controls
  853. - Point 13: Define your responsible AI use
  854. **`/arckit:secure`** → UK Government Secure by Design assessment
  855. Security compliance assessment:
  856. - NCSC Cloud Security Principles
  857. - NCSC Cyber Assessment Framework (CAF)
  858. - Cyber Essentials / Cyber Essentials Plus
  859. - UK GDPR and DPA 2018 compliance
  860. - Security architecture review
  861. - Threat modeling
  862. **`/arckit:ai-playbook`** → [UK Government AI Playbook](https://www.gov.uk/government/publications/ai-playbook-for-the-uk-government) compliance (for AI systems)
  863. Responsible AI assessment:
  864. - AI ethics principles
  865. - Transparency and explainability
  866. - Fairness and bias mitigation
  867. - Data governance for AI
  868. - Human oversight mechanisms
  869. - Impact assessment
  870. **`/arckit:atrs`** → [Algorithmic Transparency Recording Standard](https://www.gov.uk/government/collections/algorithmic-transparency-recording-standard-hub)
  871. Generate ATRS record for algorithmic decision-making:
  872. - Algorithm details and logic
  873. - Purpose and use case
  874. - Data sources and data quality
  875. - Performance metrics and monitoring
  876. - Impact assessment and mitigation
  877. **For MOD Projects**:
  878. **`/arckit:mod-secure`** → MOD Secure by Design assessment
  879. MOD-specific security compliance:
  880. - JSP 440 (Defence Project & Programme Management)
  881. - Information Assurance Maturity Model (IAMM)
  882. - MOD Security clearances and vetting
  883. - STRAP classification handling
  884. - Security Operating Procedures (SyOPs)
  885. - Supplier attestation requirements
  886. **`/arckit:jsp-936`** → [MOD JSP 936](https://www.gov.uk/government/publications/jsp-936-dependable-artificial-intelligence-ai-in-defence-part-1-directive) AI Assurance Documentation
  887. For defence projects using AI/ML systems:
  888. - JSP 936 (Dependable Artificial Intelligence in Defence)
  889. - 5 Ethical Principles (Human-Centricity, Responsibility, Understanding, Bias & Harm Mitigation, Reliability)
  890. - 5 Risk Classification Levels (Critical to Minor)
  891. - 8 AI lifecycle phases (ArcKit's grouping of JSP 936 sections 6 and 7)
  892. - Approval pathways (2PUS or Ministers by exception → Defence-Level → TLB-Level)
  893. - RAISOs and Ethics Manager governance
  894. - Human-AI teaming strategy and continuous monitoring
  895. ### Phase 14.5: Compliance Assessment (EU and French Government)
  896. ArcKit includes commands for EU regulatory compliance and French public sector governance. These commands are applicable to organisations operating in the EU or under French jurisdiction — whether public sector or private.
  897. #### EU Regulations
  898. **`/arckit:eu-rgpd`** → GDPR compliance assessment (Regulation 2016/679)
  899. Assess personal data processing obligations:
  900. - Legal basis determination (consent, contract, legitimate interest, legal obligation)
  901. - Data subject rights implementation (access, erasure, portability, objection)
  902. - CNIL registration and DPO obligations (France)
  903. - Cross-border transfer safeguards (SCCs, BCRs, adequacy decisions)
  904. - Integration with DPIA (`/arckit:dpia`) for high-risk processing
  905. **`/arckit:eu-ai-act`** → EU AI Act compliance (Regulation 2024/1689)
  906. Assess AI system obligations under the EU's risk-based AI framework:
  907. - Risk classification (unacceptable / high-risk / limited-risk / minimal)
  908. - High-risk system obligations: conformity assessment, CE marking, EUDB registration
  909. - GPAI model obligations for providers of general-purpose AI
  910. - Human oversight, transparency, and fundamental rights impact assessment
  911. - Prohibited practices (social scoring, real-time biometric surveillance)
  912. **`/arckit:eu-nis2`** → NIS2 Directive compliance (Directive 2022/2555)
  913. Assess cybersecurity obligations for essential and important entities:
  914. - Sector classification (Annex I Essential vs Annex II Important)
  915. - French OIV/OSE designation under current law (OIV: Code de la défense; OSE: loi n° 2018-133, the NIS1 transposition), pending France's NIS2 transposition bill
  916. - Governance, risk management, and incident reporting obligations
  917. - Supply chain security and vulnerability disclosure
  918. - ANSSI notification timeline (24h → 72h → 30-day final report)
  919. **`/arckit:eu-dora`** → DORA compliance (Regulation 2022/2554) for financial entities
  920. Digital Operational Resilience Act obligations for banks, insurers, and investment firms:
  921. - ICT risk management framework (5 pillars)
  922. - Major ICT-related incident classification and reporting (4h → 72h → monthly final)
  923. - TLPT (Threat-Led Penetration Testing) requirements for significant institutions
  924. - Third-party ICT provider management and critical provider designation
  925. - Contractual requirements for ICT service agreements
  926. **`/arckit:eu-cra`** → Cyber Resilience Act compliance (Regulation 2024/2847)
  927. Mandatory cybersecurity requirements for products with digital elements (hardware + software):
  928. - Product classification (Default / Important Class I / Critical Class II)
  929. - 12 Annex I Part I security-by-design requirements
  930. - SBOM in SPDX or CycloneDX format (mandatory)
  931. - Vulnerability Disclosure Policy and 24h ENISA reporting
  932. - Conformity assessment route (internal control vs notified body)
  933. - Full application deadline: 11 December 2027
  934. **`/arckit:eu-dsa`** → EU Digital Services Act compliance (Regulation 2022/2065)
  935. Tiered obligations for online intermediary services:
  936. - Provider classification (mere conduit / hosting / platform / VLOP / VLOSE)
  937. - VLOP/VLOSE designation threshold: 45M monthly active EU users
  938. - Content moderation, recommender system transparency, advertising obligations
  939. - ARCOM as French Digital Services Coordinator (DSC)
  940. - Systemic risk assessment and independent audit for VLOPs
  941. **`/arckit:eu-data-act`** → EU Data Act compliance (Regulation 2023/2854)
  942. Data sharing obligations for connected products and cloud providers:
  943. - Role determination: manufacturer / data holder / DAPS / public sector body
  944. - User data access rights (Chapter II) and B2B sharing (Chapter III)
  945. - Cloud switching obligations (Chapter VI) — switching charges withdrawn from 12 January 2027
  946. - Safeguards against unlawful international governmental access (Chapter VII, Article 32)
  947. - Application date: 12 September 2025
  948. #### French Public Sector Governance
  949. **`/arckit:fr-rgpd`** → French GDPR compliance with CNIL-specific requirements
  950. Extends EU GDPR with French context:
  951. - CNIL enforcement priorities and sector-specific guidelines
  952. - French DPO registration and CNIL prior consultation obligations
  953. - Biometric data processing under French law (CNIL authorisation required)
  954. **`/arckit:fr-ebios`** → EBIOS Risk Manager methodology (ANSSI 2018)
  955. French standard risk analysis for IS homologation:
  956. - 5-workshop structure (Framework, Risk Sources, Strategic Scenarios, Operational Scenarios, Risk Treatment)
  957. - OIV/OSE/public sector IS homologation evidence
  958. - Attack path modelling and feared events
  959. - Integration with PSSI and SecNumCloud qualification
  960. **`/arckit:fr-anssi`** → ANSSI 42 Cybersecurity Hygiene Measures assessment
  961. Assess compliance with ANSSI's foundational hygiene guide:
  962. - 10 chapters: awareness and training, knowing the IS, authentication and access control, workstations, network, administration, mobile working, updates, monitoring/audit/response, going further
  963. - ANSSI recommendations for hosting sensitive IS in the cloud (July 2024)
  964. - Gap analysis with prioritised remediation (High / Medium / Low)
  965. - Integration with EBIOS and PSSI
  966. **`/arckit:fr-anssi-carto`** → ANSSI SI Cartography (4-level IS mapping)
  967. Generate structured IS cartography following ANSSI's 4-level methodology:
  968. - Level 1: Business processes and core missions
  969. - Level 2: Application and data mapping
  970. - Level 3: Server, database, and system inventory
  971. - Level 4: Network topology, firewall rules, interconnections
  972. - Attack surface summary and sensitive flow identification
  973. **`/arckit:fr-secnumcloud`** → SecNumCloud qualification assessment
  974. Assess cloud provider and customer obligations under ANSSI's SecNumCloud referential:
  975. - Visa vs qualification distinction (only full qualification satisfies OIV/ministerial use)
  976. - IS homologation prerequisites for SecNumCloud deployment
  977. - SecNumCloud-compatible architecture requirements
  978. - Procurement clauses for public-cloud contracts
  979. **`/arckit:fr-dinum`** → DINUM digital doctrine assessment
  980. Assess compliance with French digital government doctrine:
  981. - RGI (Référentiel Général d'Interopérabilité) — interoperability standards
  982. - RGAA (Référentiel Général d'Amélioration de l'Accessibilité) — accessibility
  983. - Doctrine cloud (cloud native, cloud first, SecNumCloud for sensitive data)
  984. - SILL (Socle Interministériel de Logiciels Libres) — recommended open source stack
  985. **`/arckit:fr-marche-public`** → French public procurement (Code de la Commande Publique)
  986. Generate procurement documentation compliant with French public contract law:
  987. - Marché public thresholds and procedures (below/above EU thresholds)
  988. - Requirements statement, award criteria, and security and sovereignty clauses for the consultation file
  989. - Environmental award criterion and execution conditions (Code de la commande publique, since August 2026)
  990. - ANSSI-qualified provider requirements (PACS, PASSI, PRIS, PDIS, PAMS)
  991. - Digital State doctrine checklist (cloud, RGI, RGAA, RGESN, open source, GDPR)
  992. **`/arckit:fr-pssi`** → PSSI (Politique de Sécurité des Systèmes d'Information)
  993. Generate IS security policy for French public sector entities:
  994. - 9-section structure approved by the Highest Authority (AA)
  995. - 8 security domains (access management, network, workstations, applications, data protection, physical, business continuity, vulnerability management)
  996. - RSSI, DPO, DSI, and FSSI roles
  997. - Review cycle and integration with EBIOS and homologation
  998. **`/arckit:fr-dr`** → Diffusion Restreinte (DR) handling compliance
  999. Assess document and IS handling requirements under the DR administrative classification:
  1000. - II 901/SGDSN rules for DR document lifecycle
  1001. - Electronic storage, transmission, and physical handling obligations
  1002. - IS homologation for DR-processing systems
  1003. - Scope explicitly bounded: DR only — IGI 1300 (Secret or Très Secret) is out of scope
  1004. **`/arckit:fr-algorithme-public`** → French Public Algorithm Transparency Notice
  1005. Generate mandatory transparency notice under CRPA Art. L311-3-1:
  1006. - Scope determination: which automated decisions are covered
  1007. - Plain-language description per algorithm, parameters, and weights
  1008. - Human oversight mechanisms and appeal rights
  1009. - GDPR Art. 22 intersection (automated individual decisions)
  1010. - EU AI Act flagging for ML-based systems
  1011. - More legally binding than the UK ATRS equivalent
  1012. **`/arckit:fr-code-reuse`** → French Public Code Reuse Assessment (Circulaire PM n°6264/SG, 2021)
  1013. Assess code reuse obligations before building or procuring:
  1014. - code.gouv.fr search (French public code catalogue)
  1015. - SILL (Socle Interministériel de Logiciels Libres) — ministerially recommended open source
  1016. - EU public code alternatives (Joinup, European Commission repositories)
  1017. - Licence compatibility matrix (EUPL-1.2 recommended for public code publication)
  1018. - Decision matrix: reuse / fork / SILL adoption / procure / build
  1019. - Publication duty for source code (CRPA L300-2 / L312-1-1) and contribution-back for modified public code (Circulaire 2021)
  1020. ---
  1021. ### Phase 15: Project Story & Reporting
  1022. **`/arckit:story`** → Generate comprehensive project story
  1023. Create narrative historical record with complete timeline analysis:
  1024. - **Timeline Analysis**: 4 visualization types (Gantt chart, linear flowchart, detailed table, phase duration pie chart)
  1025. - **Timeline Metrics**: Project duration, velocity, phase analysis, critical path identification
  1026. - **Complete Timeline**: All events from git log or file modification dates with days-from-start
  1027. - **8 Narrative Chapters**: Foundation → Business Case → Requirements → Research → Procurement → Design → Delivery → Compliance
  1028. - **Traceability Demonstration**: End-to-end chains with Mermaid diagrams showing stakeholder → goals → requirements → stories → sprints
  1029. - **Governance Achievements**: Showcase compliance (TCoP, Service Standard, NCSC CAF), risk management, decision rationale
  1030. - **Strategic Context**: Wardley Map insights, build vs buy decisions, vendor selection rationale
  1031. - **Lessons Learned**: Pacing analysis, timeline deviations, recommendations for future projects
  1032. - **Comprehensive Appendices**: Artifact register, chronological activity log, DSM, command reference, glossary
  1033. **When to use**: At project milestones or completion to create shareable story for stakeholders, leadership, or portfolio reporting. Perfect for demonstrating systematic governance and ArcKit workflow value.
  1034. **`/arckit:presentation`** → Generate MARP slide deck from project artifacts
  1035. Create presentation slides from existing architecture artifacts:
  1036. - **MARP Format**: Markdown-based slides with `---` separators — exports to PDF, PPTX, or HTML
  1037. - **Focus Modes**: Executive (board-level), Technical (architecture detail), Stakeholder (benefits-focused), Procurement (RFP briefings)
  1038. - **Artifact-Driven**: Reads all available project artifacts and extracts key content into slides
  1039. - **Mermaid Diagrams**: Gantt charts, C4 diagrams, pie charts, and quadrant charts embedded natively
  1040. - **Configurable**: Choose slide count (6-8, 10-12, 15-20) and MARP theme (default, gaia, uncover)
  1041. - **Doc type code**: `PRES`
  1042. **When to use**: Before governance boards, stakeholder briefings, gate reviews, or quarterly portfolio presentations. Run after creating most project artifacts for the richest slide deck.
  1043. ### Phase 16: Documentation Publishing
  1044. **`/arckit:pages`** → Generate documentation site
  1045. Publish all project documentation as an interactive website:
  1046. - **Static Site Generation**: Generates `docs/index.html` and `docs/manifest.json` — deployable to any static host (GitHub Pages, Netlify, Vercel, S3, etc.)
  1047. - **Mermaid Diagram Rendering**: All architecture diagrams render inline with mermaid.js
  1048. - **Project Navigation**: Sidebar with collapsible project tree, document categories, and version badges — documents with multiple versions show an inline dropdown selector
  1049. - **GOV.UK Styling**: Professional government design system styling
  1050. - **Document Index**: Manifest.json provides programmatic access to all artifacts
  1051. - **LLM Discovery**: Generates `docs/llms.txt` ([llmstxt.org](https://llmstxt.org/) format) so LLM agents and crawlers can index every artifact, guide, and project. Hand-curated `docs/llms.txt` files (without the ArcKit generation marker) are preserved on re-runs
  1052. **When to use**: When you want to share project documentation with stakeholders via a professional web interface, or to create a portfolio view of all architecture artifacts.
  1053. ---
  1054. ## Supported AI Assistants
  1055. | Assistant | Support | Notes |
  1056. |-----------|---------|-------|
  1057. | [Claude Code](https://www.anthropic.com/claude-code) | ✅ Premier | **Primary platform.** Plugin with agents, hooks, MCP servers, and auto-updates |
  1058. | [Gemini CLI](https://github.com/google-gemini/gemini-cli) | ✅ Full | Extension with commands, MCP servers, and auto-updates |
  1059. | [GitHub Copilot](https://github.com/features/copilot) | ✅ Core | VS Code prompt files, custom agents, and repo-wide instructions (`arckit init --ai copilot`) |
  1060. | [OpenAI Codex CLI](https://chatgpt.com/features/codex) | ✅ Core | CLI with commands and templates. ChatGPT Plus/Pro/Enterprise ([Setup Guide](.codex/README.md)) |
  1061. | [OpenCode CLI](https://opencode.net/cli) | ✅ Core | CLI with commands and templates |
  1062. > **Platform Support**: ArcKit is developed and tested on **Linux**. Windows has limited support — hooks (session init, project context, filename validation, MCP auto-allow) require bash and jq which are not available on stock Windows. For the best experience on Windows, use a **devcontainer** or **WSL2**.
  1063. ### Why Claude Code?
  1064. Claude Code is the **primary development platform** for ArcKit and provides capabilities not available in other formats:
  1065. | Feature | Claude Code | Gemini CLI | Copilot | Codex / OpenCode |
  1066. |---------|:-----------:|:----------:|:-------:|:----------------:|
  1067. | 75 cross-AI slash commands | ✅ | ✅ | ✅ | ✅ |
  1068. | `/arckit:build` parallel build harness (Claude-only — depends on parallel `Agent` dispatch) | ✅ | — | — | — |
  1069. | Templates & scripts | ✅ | ✅ | ✅ | ✅ |
  1070. | Bundled MCP servers (AWS, Azure, GCP, DataCommons, govreposcrape) | ✅ | ✅ (3 servers) | — | Manual setup |
  1071. | **Autonomous research agents** (10 agents for research, datascout, cloud research, gov code discovery, grants, framework) | ✅ | — | ✅ (10 agents) | — |
  1072. | **SessionStart hook** (auto-detect version + projects) | ✅ | — | — | — |
  1073. | **UserPromptSubmit hook** (project context injection on every prompt) | ✅ | — | — | — |
  1074. | **PreToolUse hook** (ARC filename auto-correction) | ✅ | — | — | — |
  1075. | **PermissionRequest hook** (auto-allow MCP documentation tools) | ✅ | — | — | — |
  1076. | **Per-command Stop hooks** (output validation, e.g. Wardley Map math checks) | ✅ | — | — | — |
  1077. | Wardley Mapping skill (with Pinecone MCP book corpus) | ✅ | — | — | — |
  1078. | Mermaid Syntax Reference skill (23 diagram types + config) | ✅ | ✅ | — | ✅ |
  1079. | Automatic marketplace updates | ✅ | ✅ | Manual reinstall | Manual reinstall |
  1080. | Zero-config installation | ✅ | ✅ | `arckit init` required | `arckit init` required |
  1081. **Agents** run research-heavy commands (market research, data source discovery, cloud service evaluation) in isolated context windows, keeping the main conversation clean and enabling dozens of WebSearch/WebFetch/MCP calls without context bloat.
  1082. **Hooks** provide automated governance: filenames are auto-corrected to ArcKit conventions, project context is injected into every prompt so commands know what artifacts exist, MCP tools are auto-approved, and generated outputs like Wardley Maps are validated for mathematical consistency before being finalized.
  1083. Gemini CLI provides a strong experience with all commands and MCP servers but lacks agent delegation and hooks. GitHub Copilot provides all 76 official commands as prompt files and 10 custom agents but lacks hooks and MCP servers. Codex CLI and OpenCode CLI provide core command functionality but require manual setup and `arckit init` scaffolding.
  1084. ### Why Commands, Not Skills
  1085. Claude Code automatically exposes ArcKit commands as **skills** (they appear in the skills list and can be matched by natural language). ArcKit intentionally uses **slash commands** rather than standalone skills because:
  1086. - **Deliberate invocation required** — Every command generates a heavyweight governance document (requirements spec, risk register, DPIA, etc.). Auto-triggering from conversational intent would waste significant time and tokens.
  1087. - **Dependency ordering** — Commands follow a deliberate sequence (principles → stakeholders → requirements → data-model → etc.). Skills that auto-trigger could run out of order.
  1088. - **User input via `$ARGUMENTS`** — Most commands accept context from the user (project name, scope, constraints). The command system handles this with `$ARGUMENTS` substitution.
  1089. - **Best of both worlds** — Since Claude Code exposes commands as skills automatically, users get explicit `/arckit:requirements` invocation AND natural language matching when Claude recognises intent — no restructuring needed.
  1090. ### Using with GitHub Copilot
  1091. For GitHub Copilot users in VS Code, ArcKit commands are delivered as prompt files and custom agents:
  1092. ```bash
  1093. # Install and create project (3 steps, zero config)
  1094. pip install git+https://github.com/tractorjuice/arc-kit.git
  1095. arckit init my-project --ai copilot
  1096. cd my-project && code .
  1097. # Then use ArcKit commands in Copilot Chat
  1098. /arckit-principles Create principles for financial services
  1099. /arckit-stakeholders Analyze stakeholders for cloud migration
  1100. /arckit-requirements Create comprehensive requirements
  1101. ```
  1102. This creates `.github/prompts/arckit-*.prompt.md`, `.github/agents/arckit-*.agent.md` (10 custom agents), and `.github/copilot-instructions.md` (repo-wide context).
  1103. ### Using with Codex CLI
  1104. For OpenAI Codex CLI users, ArcKit commands are delivered as skills and auto-discovered:
  1105. ```bash
  1106. # Install and create project (3 steps, zero config)
  1107. pip install git+https://github.com/tractorjuice/arc-kit.git
  1108. arckit init my-project --ai codex
  1109. cd my-project && codex
  1110. # Then use ArcKit skills
  1111. $arckit-principles Create principles for financial services
  1112. $arckit-stakeholders Analyze stakeholders for cloud migration
  1113. $arckit-requirements Create comprehensive requirements
  1114. ```
  1115. See [.codex/README.md](.codex/README.md) for full Codex CLI setup and usage.
  1116. ## Project Structure
  1117. ArcKit creates this structure:
  1118. ```text
  1119. payment-modernization/
  1120. ├── .arckit/
  1121. │ ├── scripts/
  1122. │ │ └── bash/ # Automation scripts
  1123. │ ├── templates/ # Default templates (refreshed by arckit init)
  1124. │ └── templates-custom/ # Your customizations (preserved across updates)
  1125. ├── projects/
  1126. │ ├── 000-global/
  1127. │ │ └── ARC-000-PRIN-v1.0.md # Global principles
  1128. │ └── 001-payment-gateway/
  1129. │ ├── ARC-001-STKE-v1.0.md # Stakeholder analysis
  1130. │ ├── ARC-001-RISK-v1.0.md # Risk register (Orange Book)
  1131. │ ├── ARC-001-SOBC-v1.0.md # Strategic Outline Business Case
  1132. │ ├── ARC-001-REQ-v1.0.md # Comprehensive requirements
  1133. │ ├── ARC-001-DATA-v1.0.md # Data model with ERD, GDPR compliance
  1134. │ ├── wardley-maps/ # Strategic Wardley Maps
  1135. │ │ ├── ARC-001-WARD-001-v1.0.md # Current architecture positioning
  1136. │ │ ├── ARC-001-WARD-002-v1.0.md # Target architecture vision
  1137. │ │ ├── ARC-001-WARD-003-v1.0.md # Gap analysis
  1138. │ │ └── ARC-001-WARD-004-v1.0.md # Build vs buy decisions
  1139. │ ├── ARC-001-SOW-v1.0.md # Statement of Work (RFP)
  1140. │ ├── ARC-001-EVAL-v1.0.md # Vendor evaluation framework
  1141. │ ├── vendors/
  1142. │ │ ├── acme-corp/
  1143. │ │ │ ├── proposal.pdf
  1144. │ │ │ ├── scoring.md
  1145. │ │ │ ├── hld-v1.md
  1146. │ │ │ └── reviews/
  1147. │ │ │ └── hld-v1-review.md
  1148. │ │ ├── beta-systems/
  1149. │ │ │ └── ...
  1150. │ │ └── comparison.md
  1151. │ ├── ARC-001-SNOW-v1.0.md # Service management design
  1152. │ ├── ARC-001-TRAC-v1.0.md # Traceability matrix
  1153. │ └── final/
  1154. │ ├── selected-vendor.md
  1155. │ ├── approved-hld.md
  1156. │ └── dld/
  1157. ├── .agents/skills/ # Codex CLI skills (auto-discovered)
  1158. ├── .codex/
  1159. │ ├── agents/ # Agent configs
  1160. │ └── config.toml # MCP servers + agent roles
  1161. ├── .github/
  1162. │ ├── prompts/arckit-*.prompt.md # GitHub Copilot prompt files (70 official + community overlays)
  1163. │ ├── agents/arckit-*.agent.md # GitHub Copilot custom agents (10 agents)
  1164. │ └── copilot-instructions.md # Repo-wide Copilot context
  1165. └── .opencode/commands/ # OpenCode CLI commands
  1166. ```
  1167. ---
  1168. ## Template Customization
  1169. Customize ArcKit templates without modifying defaults:
  1170. ```bash
  1171. # Inside your AI assistant
  1172. /arckit:customize requirements # Copy requirements template for editing
  1173. /arckit:customize all # Copy all templates
  1174. /arckit:customize list # See available templates
  1175. ```
  1176. **How it works:**
  1177. - Default templates live in `.arckit/templates/` (refreshed by `arckit init`)
  1178. - Your customizations go in `.arckit/templates-custom/` (preserved across updates)
  1179. - Commands automatically check for custom templates first, falling back to defaults
  1180. **Common customizations:**
  1181. - Add organization-specific document control fields
  1182. - Include mandatory compliance sections (ISO 27001, PCI-DSS)
  1183. - Add department-specific approval workflows
  1184. - Customize UK Government classification banners
  1185. ---
  1186. ## Complete Command Reference
  1187. Core ArcKit commands with maturity status and example outputs from public test repositories.
  1188. ### Status Legend
  1189. | Status | Description |
  1190. |--------|-------------|
  1191. | 🟢 **Live** | Production-ready, extensively tested |
  1192. | 🔵 **Beta** | Feature-complete, actively refined |
  1193. | 🟠 **Alpha** | Working, limited testing |
  1194. | 🟣 **Experimental** | New in v0.11.x, early adopters |
  1195. ### Example Repositories
  1196. | Code | Repository | Description |
  1197. |------|------------|-------------|
  1198. | v1 | [arckit-test-project-v1-m365](https://github.com/tractorjuice/arckit-test-project-v1-m365) | Microsoft 365 GCC-H Migration |
  1199. | v2 | [arckit-test-project-v2-hmrc-chatbot](https://github.com/tractorjuice/arckit-test-project-v2-hmrc-chatbot) | HMRC Tax Assistant Chatbot |
  1200. | v3 | [arckit-test-project-v3-windows11](https://github.com/tractorjuice/arckit-test-project-v3-windows11) | Windows 11 Enterprise Deployment |
  1201. | v6 | [arckit-test-project-v6-patent-system](https://github.com/tractorjuice/arckit-test-project-v6-patent-system) | IPO Patent Application System |
  1202. | v7 | [arckit-test-project-v7-nhs-appointment](https://github.com/tractorjuice/arckit-test-project-v7-nhs-appointment) | NHS Appointment Booking |
  1203. | v8 | [arckit-test-project-v8-ons-data-platform](https://github.com/tractorjuice/arckit-test-project-v8-ons-data-platform) | ONS Data Platform Modernisation |
  1204. | v9 | [arckit-test-project-v9-cabinet-office-genai](https://github.com/tractorjuice/arckit-test-project-v9-cabinet-office-genai) | Cabinet Office GenAI Platform |
  1205. | v10 | [arckit-test-project-v10-training-marketplace](https://github.com/tractorjuice/arckit-test-project-v10-training-marketplace) | UK Government Training Marketplace |
  1206. | v11 | [arckit-test-project-v11-national-highways-data](https://github.com/tractorjuice/arckit-test-project-v11-national-highways-data) | National Highways Data Architecture |
  1207. | v13 | [arckit-test-project-v13-plymouth-research](https://github.com/tractorjuice/arckit-test-project-v13-plymouth-research) | Plymouth Restaurant Web Scraping |
  1208. | v14 | [arckit-test-project-v14-scottish-courts](https://github.com/tractorjuice/arckit-test-project-v14-scottish-courts) | Scottish Courts GenAI Strategy |
  1209. | v16 | [arckit-test-project-v16-doctors-appointment](https://github.com/tractorjuice/arckit-test-project-v16-doctors-appointment) | Doctors Online Appointment System |
  1210. | v17 | [arckit-test-project-v17-fuel-prices](https://github.com/tractorjuice/arckit-test-project-v17-fuel-prices) | UK Government Fuel Price Transparency Service |
  1211. | v18 | [arckit-test-project-v18-smart-meter](https://github.com/tractorjuice/arckit-test-project-v18-smart-meter) | UK Smart Meter Data Consumer App |
  1212. | v19 | [arckit-test-project-v19-gov-api-aggregator](https://github.com/tractorjuice/arckit-test-project-v19-gov-api-aggregator) | UK Government API Aggregator |
  1213. | v21 | [arckit-test-project-v21-criminal-courts](https://github.com/tractorjuice/arckit-test-project-v21-criminal-courts) | Independent Review of the Criminal Courts — Tech & AI |
  1214. | v22 | [arckit-test-project-v22-genai-playbook](https://github.com/tractorjuice/arckit-test-project-v22-genai-playbook) | UK Government GenAI Playbook |
  1215. | v45 | [arckit-test-project-v45-nsi-rainbow](https://github.com/tractorjuice/arckit-test-project-v45-nsi-rainbow) | NS&I Digital Modernisation Programme (Project Rainbow) |
  1216. | v46 | [arckit-test-project-v46-gds-local](https://github.com/tractorjuice/arckit-test-project-v46-gds-local) | GDS Local |
  1217. | v46 | [arckit-test-project-v46-sdg](https://github.com/tractorjuice/arckit-test-project-v46-sdg) | ArcKit SDG Mono-Repo (17 UN SDGs, 78 UK Gov projects) |
  1218. | v47 | [arckit-test-project-v47-dft-transforming-city-regions](https://github.com/tractorjuice/arckit-test-project-v47-dft-transforming-city-regions) | DfT Transforming City Regions funding system |
  1219. | v50 | [arckit-test-project-v50-post-office-horizon](https://github.com/tractorjuice/arckit-test-project-v50-post-office-horizon) | Post Office Horizon |
  1220. | v51 | [arckit-test-project-v51-prs-database](https://github.com/tractorjuice/arckit-test-project-v51-prs-database) | UK PRS Database under the Renters' Rights Act 2025 |
  1221. | v52 | [arckit-test-project-v52-uae-caio-playbook](https://github.com/tractorjuice/arckit-test-project-v52-uae-caio-playbook) | UAE CAIO Playbook for the 24-month agentic AI mandate |
  1222. ### Foundation
  1223. | Command | Description | Examples | Status |
  1224. |---------|-------------|----------|--------|
  1225. | `/arckit:init` | Initialize ArcKit project structure with numbered project directories and global artifacts | — | 🟢 Live |
  1226. | `/arckit:start` | Get oriented with ArcKit — check project status, explore available commands, and choose your next step | — | 🟢 Live |
  1227. | `/arckit:plan` | Create project plan with timeline, phases, gates, and Mermaid diagrams | [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-PLAN-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/ARC-002-PLAN-v1.0.md) [v3/004](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/004-conference-facilities-modernization/ARC-004-PLAN-v1.0.md) [v3/005](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/005-cloud-pki/ARC-005-PLAN-v1.0.md) [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/#projects/001-ons-data-platform-modernisation/ARC-001-PLAN-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-PLAN-v1.0.md) [v10](https://tractorjuice.github.io/arckit-test-project-v10-training-marketplace/#projects/001-ai-training-marketplace/ARC-001-PLAN-v1.0.md) [v11](https://tractorjuice.github.io/arckit-test-project-v11-national-highways-data/#projects/001-national-highways-data-architecture-modernization/ARC-001-PLAN-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-PLAN-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/ARC-001-PLAN-v1.0.md) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/#projects/001-smart-meter-app/ARC-001-PLAN-v1.0.md) | 🟢 Live |
  1228. | `/arckit:principles` | Create or update enterprise architecture principles | [v1](https://tractorjuice.github.io/arckit-test-project-v1-m365/#projects/000-global/ARC-000-PRIN-v1.0.md) [v2](https://tractorjuice.github.io/arckit-test-project-v2-hmrc-chatbot/#projects/000-global/ARC-000-PRIN-v1.0.md) [v3](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/000-global/ARC-000-PRIN-v1.0.md) [v6](https://tractorjuice.github.io/arckit-test-project-v6-patent-system/#projects/000-global/ARC-000-PRIN-v1.0.md) [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/#projects/000-global/ARC-000-PRIN-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/000-global/ARC-000-PRIN-v1.0.md) [v10](https://tractorjuice.github.io/arckit-test-project-v10-training-marketplace/#projects/000-global/ARC-000-PRIN-v1.0.md) [v11](https://tractorjuice.github.io/arckit-test-project-v11-national-highways-data/#projects/000-global/ARC-000-PRIN-v1.0.md) [v7](https://tractorjuice.github.io/arckit-test-project-v7-nhs-appointment/#projects/000-global/ARC-000-PRIN-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/000-global/ARC-000-PRIN-v1.0.md) [v16](https://tractorjuice.github.io/arckit-test-project-v16-doctors-appointment/#projects/000-global/ARC-000-PRIN-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/000-global/ARC-000-PRIN-v1.0.md) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/#projects/000-global/ARC-000-PRIN-v1.0.md) [v19](https://tractorjuice.github.io/arckit-test-project-v19-gov-api-aggregator/#projects/000-global/ARC-000-PRIN-v1.0.md) | 🟢 Live |
  1229. ### Interoperability
  1230. | Command | Description | Examples | Status |
  1231. |---------|-------------|----------|--------|
  1232. | `/arckit:export-okf` | Export ArcKit project artifacts as an OKF Markdown bundle without changing source ARC files | — | 🔵 Beta |
  1233. | `/arckit:import-okf` | Import an OKF Markdown bundle into ArcKit as reviewable research notes with a JSON report | — | 🔵 Beta |
  1234. ### Strategic Context
  1235. | Command | Description | Examples | Status |
  1236. |---------|-------------|----------|--------|
  1237. | `/arckit:stakeholders` | Analyze stakeholder drivers, goals, and measurable outcomes | [v1](https://tractorjuice.github.io/arckit-test-project-v1-m365/#projects/001-exchange-online-migration/ARC-001-STKE-v1.0.md) [v2](https://tractorjuice.github.io/arckit-test-project-v2-hmrc-chatbot/#projects/001-hmrc-chatbot/ARC-001-STKE-v1.0.md) [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-STKE-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/ARC-002-STKE-v1.0.md) [v3/003](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/003-peripherals-update-upgrade/ARC-003-STKE-v1.0.md) [v3/004](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/004-conference-facilities-modernization/ARC-004-STKE-v1.0.md) [v3/005](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/005-cloud-pki/ARC-005-STKE-v1.0.md) [v3/006](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/006-large-format-printer/ARC-006-STKE-v1.0.md) [v3/007](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/007-vpn-service-windows11-autopilot/ARC-007-STKE-v1.0.md) [v6](https://tractorjuice.github.io/arckit-test-project-v6-patent-system/#projects/001-patent-management-system-for-the-intellectual-property-office/ARC-001-STKE-v1.0.md) [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/#projects/001-ons-data-platform-modernisation/ARC-001-STKE-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-STKE-v1.0.md) [v10](https://tractorjuice.github.io/arckit-test-project-v10-training-marketplace/#projects/001-ai-training-marketplace/ARC-001-STKE-v1.0.md) [v11](https://tractorjuice.github.io/arckit-test-project-v11-national-highways-data/#projects/001-national-highways-data-architecture-modernization/ARC-001-STKE-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-STKE-v1.0.md) [v16](https://tractorjuice.github.io/arckit-test-project-v16-doctors-appointment/#projects/001-doctors-appointment/ARC-001-STKE-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/ARC-001-STKE-v1.0.md) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/#projects/001-smart-meter-app/ARC-001-STKE-v1.0.md) [v19](https://tractorjuice.github.io/arckit-test-project-v19-gov-api-aggregator/#projects/001-uk-government-api-aggregator/ARC-001-STKE-v1.0.md) | 🟢 Live |
  1238. | `/arckit:risk` | Create comprehensive risk register following HM Treasury Orange Book principles | [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-RISK-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/ARC-002-RISK-v1.0.md) [v3/003](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/003-peripherals-update-upgrade/ARC-003-RISK-v1.0.md) [v3/004](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/004-conference-facilities-modernization/ARC-004-RISK-v1.0.md) [v3/005](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/005-cloud-pki/ARC-005-RISK-v1.0.md) [v3/006](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/006-large-format-printer/ARC-006-RISK-v1.0.md) [v3/007](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/007-vpn-service-windows11-autopilot/ARC-007-RISK-v1.0.md) [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/#projects/001-ons-data-platform-modernisation/ARC-001-RISK-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-RISK-v1.0.md) [v11](https://tractorjuice.github.io/arckit-test-project-v11-national-highways-data/#projects/001-national-highways-data-architecture-modernization/ARC-001-RISK-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-RISK-v1.0.md) [v16](https://tractorjuice.github.io/arckit-test-project-v16-doctors-appointment/#projects/001-doctors-appointment/ARC-001-RISK-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/ARC-001-RISK-v1.0.md) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/#projects/001-smart-meter-app/ARC-001-RISK-v1.0.md) | 🟢 Live |
  1239. | `/arckit:sobc` | Create Strategic Outline Business Case (SOBC) using UK Government Green Book 5-case model | [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-SOBC-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/ARC-002-SOBC-v1.0.md) [v3/003](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/003-peripherals-update-upgrade/ARC-003-SOBC-v1.0.md) [v3/004](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/004-conference-facilities-modernization/ARC-004-SOBC-v1.0.md) [v3/005](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/005-cloud-pki/ARC-005-SOBC-v1.0.md) [v3/007](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/007-vpn-service-windows11-autopilot/ARC-007-SOBC-v1.0.md) [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/#projects/001-ons-data-platform-modernisation/ARC-001-SOBC-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-SOBC-v1.0.md) | 🟢 Live |
  1240. ### Requirements & Data
  1241. | Command | Description | Examples | Status |
  1242. |---------|-------------|----------|--------|
  1243. | `/arckit:requirements` | Create comprehensive business and technical requirements | [v1](https://tractorjuice.github.io/arckit-test-project-v1-m365/#projects/001-exchange-online-migration/ARC-001-REQ-v1.0.md) [v2](https://tractorjuice.github.io/arckit-test-project-v2-hmrc-chatbot/#projects/001-hmrc-chatbot/ARC-001-REQ-v1.0.md) [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-REQ-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/ARC-002-REQ-v1.0.md) [v3/003](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/003-peripherals-update-upgrade/ARC-003-REQ-v1.0.md) [v3/004](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/004-conference-facilities-modernization/ARC-004-REQ-v1.0.md) [v3/005](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/005-cloud-pki/ARC-005-REQ-v1.0.md) [v3/006](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/006-large-format-printer/ARC-006-REQ-v1.0.md) [v3/007](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/007-vpn-service-windows11-autopilot/ARC-007-REQ-v1.0.md) [v6](https://tractorjuice.github.io/arckit-test-project-v6-patent-system/#projects/001-patent-management-system-for-the-intellectual-property-office/ARC-001-REQ-v1.0.md) [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/#projects/001-ons-data-platform-modernisation/ARC-001-REQ-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-REQ-v1.0.md) [v10](https://tractorjuice.github.io/arckit-test-project-v10-training-marketplace/#projects/001-ai-training-marketplace/ARC-001-REQ-v1.0.md) [v11](https://tractorjuice.github.io/arckit-test-project-v11-national-highways-data/#projects/001-national-highways-data-architecture-modernization/ARC-001-REQ-v1.0.md) [v7](https://tractorjuice.github.io/arckit-test-project-v7-nhs-appointment/#projects/001-nhs-appointment-booking/ARC-001-REQ-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-REQ-v1.0.md) [v16](https://tractorjuice.github.io/arckit-test-project-v16-doctors-appointment/#projects/001-doctors-appointment/ARC-001-REQ-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/ARC-001-REQ-v1.0.md) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/#projects/001-smart-meter-app/ARC-001-REQ-v1.0.md) [v19](https://tractorjuice.github.io/arckit-test-project-v19-gov-api-aggregator/#projects/001-uk-government-api-aggregator/ARC-001-REQ-v1.0.md) | 🟢 Live |
  1244. | `/arckit:data-model` | Create comprehensive data model with entity relationships, GDPR compliance, and data governance | [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-DATA-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/ARC-002-DATA-v1.0.md) [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/#projects/001-ons-data-platform-modernisation/ARC-001-DATA-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-DATA-v1.0.md) [v10](https://tractorjuice.github.io/arckit-test-project-v10-training-marketplace/#projects/001-ai-training-marketplace/ARC-001-DATA-v1.0.md) [v11](https://tractorjuice.github.io/arckit-test-project-v11-national-highways-data/#projects/001-national-highways-data-architecture-modernization/ARC-001-DATA-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-DATA-v1.0.md) [v16](https://tractorjuice.github.io/arckit-test-project-v16-doctors-appointment/#projects/001-doctors-appointment/ARC-001-DATA-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/ARC-001-DATA-v1.0.md) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/#projects/001-smart-meter-app/ARC-001-DATA-v1.0.md) | 🟢 Live |
  1245. | `/arckit:data-mesh-contract` | Create federated data product contracts for mesh architectures with SLAs, governance, and interoperability guarantees | — | 🟠 Alpha |
  1246. | `/arckit:dpia` | Generate [Data Protection Impact Assessment (DPIA)](https://ico.org.uk/for-organisations/uk-gdpr-guidance-and-resources/accountability-and-governance/data-protection-impact-assessments-dpias/) for UK GDPR Article 35 compliance | [v3](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-DPIA-v1.0.md) [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/#projects/001-ons-data-platform-modernisation/ARC-001-DPIA-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-DPIA-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-DPIA-v1.0.md) [v16](https://tractorjuice.github.io/arckit-test-project-v16-doctors-appointment/#projects/001-doctors-appointment/ARC-001-DPIA-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/ARC-001-DPIA-v1.0.md) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/#projects/001-smart-meter-app/ARC-001-DPIA-v1.0.md) | 🔵 Beta |
  1247. ### Research & Strategy
  1248. | Command | Description | Examples | Status |
  1249. |---------|-------------|----------|--------|
  1250. | `/arckit:platform-design` | Create platform strategy using Platform Design Toolkit (8 canvases for multi-sided ecosystems) | [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/#projects/001-ons-data-platform-modernisation/ARC-001-GAAP-v1.0.md) [v10](https://tractorjuice.github.io/arckit-test-project-v10-training-marketplace/#projects/001-ai-training-marketplace/ARC-001-PLAT-v1.0.md) | 🟣 Experimental |
  1251. | `/arckit:research` | Research the technology, services and products that could meet the requirements, with checked facts and published costs | [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-RSCH-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/ARC-002-RSCH-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/research/ARC-001-RSCH-001-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/ARC-001-RSCH-v1.0.md) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/#projects/001-smart-meter-app/ARC-001-RSCH-v1.0.md) | 🔵 Beta |
  1252. | `/arckit:grants` | Research UK government grants, charitable funding, and accelerator programmes with eligibility scoring | — | 🟣 Experimental |
  1253. | `/arckit:wardley` | Create strategic Wardley Maps for architecture decisions and build vs buy analysis | [v3](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/wardley-maps/ARC-001-WARD-001-v1.0.md) [v6](https://tractorjuice.github.io/arckit-test-project-v6-patent-system/#projects/001-patent-management-system-for-the-intellectual-property-office/wardley-maps/ARC-001-WARD-001-v1.0.md) [v11](https://tractorjuice.github.io/arckit-test-project-v11-national-highways-data/#projects/001-national-highways-data-architecture-modernization/wardley-maps/ARC-001-WARD-001-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/wardley-maps/ARC-001-WARD-001-v1.0.md) | 🟣 Experimental |
  1254. | `/arckit:wardley.value-chain` | Decompose user needs into value chains for Wardley Mapping | — | 🟣 Experimental |
  1255. | `/arckit:wardley.doctrine` | Assess organizational doctrine maturity (4 phases, 40+ principles) | — | 🟣 Experimental |
  1256. | `/arckit:wardley.gameplay` | Analyze strategic plays from 60+ gameplay patterns | — | 🟣 Experimental |
  1257. | `/arckit:wardley.climate` | Assess 32 climatic patterns affecting mapped components | — | 🟣 Experimental |
  1258. | `/arckit:strategy` | Synthesise strategic artifacts into executive-level Architecture Strategy document | — | 🔵 Beta |
  1259. | `/arckit:roadmap` | Create strategic architecture roadmap with multi-year timeline, capability evolution, and governance | [v3](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-ROAD-v1.0.md) | 🔵 Beta |
  1260. | `/arckit:framework` | Transform architecture artifacts into a structured, reusable framework with principles, patterns, and implementation guidance | — | 🔵 Beta |
  1261. | `/arckit:adr` | Document architectural decisions with options analysis and traceability | [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/decisions/ARC-001-ADR-001-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/decisions/ARC-002-ADR-001-v1.0.md) [v3/003](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/003-peripherals-update-upgrade/decisions/ARC-003-ADR-001-v1.0.md) [v3/004](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/004-conference-facilities-modernization/decisions/ARC-004-ADR-001-v1.0.md) [v3/005](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/005-cloud-pki/decisions/ARC-005-ADR-001-v1.0.md) [v3/007](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/007-vpn-service-windows11-autopilot/decisions/ARC-007-ADR-001-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/decisions/ARC-001-ADR-001-v1.0.md) | 🔵 Beta |
  1262. ### Cloud Research (MCP)
  1263. These commands use [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) servers to access authoritative cloud provider documentation in real-time. The Claude Code plugin bundles both MCP servers automatically. Gemini and Codex users need to install them separately.
  1264. | Command | Description | Examples | Status |
  1265. |---------|-------------|----------|--------|
  1266. | `/arckit:azure-research` | Research Azure services and architecture patterns using [Microsoft Learn MCP](https://www.npmjs.com/package/@anthropic/mcp-server-microsoft-docs) | [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/research/ARC-001-AZRS-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/research/ARC-002-AZRS-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/research/ARC-001-AZRS-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/research/ARC-001-AZRS-v1.0.md) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/#projects/001-smart-meter-app/research/ARC-001-AZRS-v1.0.md) [v19](https://tractorjuice.github.io/arckit-test-project-v19-gov-api-aggregator/#projects/001-uk-government-api-aggregator/research/ARC-001-AZRS-v1.0.md) | 🟣 Experimental |
  1267. | `/arckit:aws-research` | Research AWS services and architecture patterns using [AWS Knowledge MCP](https://awslabs.github.io/mcp/servers/aws-knowledge-mcp-server) | [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/research/ARC-001-AWRS-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/research/ARC-001-AWRS-v1.0.md) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/#projects/001-smart-meter-app/research/ARC-001-AWRS-v1.0.md) [v19](https://tractorjuice.github.io/arckit-test-project-v19-gov-api-aggregator/#projects/001-uk-government-api-aggregator/research/ARC-001-AWRS-v1.0.md) | 🟣 Experimental |
  1268. | `/arckit:gcp-research` | Research Google Cloud services and architecture patterns using [Google Developer Knowledge MCP](https://developerknowledge.googleapis.com/mcp) | — | 🟣 Experimental |
  1269. ### Data Source Discovery
  1270. | Command | Description | Examples | Status |
  1271. |---------|-------------|----------|--------|
  1272. | `/arckit:datascout` | Discover external data sources (APIs, datasets, open data portals) to fulfil project requirements | [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/ARC-001-DSCT-v1.0.md) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/#projects/001-smart-meter-app/ARC-001-DSCT-v1.0.md) [v19](https://tractorjuice.github.io/arckit-test-project-v19-gov-api-aggregator/#projects/001-uk-government-api-aggregator/ARC-001-DSCT-v1.0.md) | 🟣 Experimental |
  1273. > **Note**: The Google Developer Knowledge MCP requires an API key (`GOOGLE_API_KEY` environment variable). See the [GCP Research guide](docs/guides/gcp-research.md) for setup instructions.
  1274. ### Procurement Market Intelligence
  1275. | Command | Description | Examples | Status |
  1276. |---------|-------------|----------|--------|
  1277. | `/arckit:tenders` | Procurement market intelligence — award-value benchmarks, top suppliers, incumbency and concentration, from the UK Tenders MCP | — | 🟣 Experimental |
  1278. | `/arckit:competitors` | Competitor landscape — rival suppliers, awarded-value market share, head-to-head and concentration, from the UK Tenders MCP | — | 🟣 Experimental |
  1279. > **Note**: `/arckit:tenders` and `/arckit:competitors` both use the bundled `uk-tenders` MCP server (keyless, always loaded) via the shared `arckit-tenders-reader` subagent. Data: more than 700,000 UK contracting processes (October 2026) across FTS, Contracts Finder, Public Contracts Scotland, Sell2Wales, and eTendersNI; nightly refresh; best-effort availability (no formal SLA). `/arckit:tenders` outputs a `TNDR` artefact (market-wide benchmarks, incumbency, concentration). `/arckit:competitors` outputs a `CMPT` artefact (rival-supplier landscape, market-share ranking, head-to-head).
  1280. ### Government Code Discovery
  1281. These commands use the [govreposcrape MCP](https://github.com/chrisns/govreposcrape) server to search 24,500+ UK government repositories. The Claude Code plugin bundles the MCP server automatically. No API key required.
  1282. | Command | Description | Examples | Status |
  1283. |---------|-------------|----------|--------|
  1284. | `/arckit:gov-code-search` | Search 24,500+ UK government repositories using natural language | — | 🟣 Experimental |
  1285. | `/arckit:gov-landscape` | Map the UK government code landscape for a domain | — | 🟣 Experimental |
  1286. | `/arckit:gov-reuse` | Discover reusable UK government code before building from scratch | — | 🟣 Experimental |
  1287. ### Procurement
  1288. | Command | Description | Examples | Status |
  1289. |---------|-------------|----------|--------|
  1290. | `/arckit:sow` | Generate Statement of Work (SOW) / RFP document for vendor procurement | [v1](https://tractorjuice.github.io/arckit-test-project-v1-m365/#projects/001-exchange-online-migration/ARC-001-SOW-v1.0.md) [v2](https://tractorjuice.github.io/arckit-test-project-v2-hmrc-chatbot/#projects/001-hmrc-chatbot/ARC-001-SOW-v1.0.md) [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-SOW-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/ARC-002-SOW-v1.0.md) [v3/003](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/003-peripherals-update-upgrade/ARC-003-SOW-v1.0.md) [v6](https://tractorjuice.github.io/arckit-test-project-v6-patent-system/#projects/001-patent-management-system-for-the-intellectual-property-office/ARC-001-SOW-v1.0.md) | 🟢 Live |
  1291. | `/arckit:dos` | Generate Digital Outcomes and Specialists (DOS7) procurement documentation for the Contract Award Service | — | 🟣 Experimental |
  1292. | `/arckit:gcloud-search` | Find G-Cloud services on UK Digital Marketplace with live search and comparison | [v3](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-GCLD-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-GCLD-v1.0.md) | 🟣 Experimental |
  1293. | `/arckit:gcloud-clarify` | Analyze G-Cloud service gaps and generate supplier clarification questions | — | 🟣 Experimental |
  1294. | `/arckit:evaluate` | Create vendor evaluation framework and score vendor proposals | [v1](https://tractorjuice.github.io/arckit-test-project-v1-m365/#projects/001-exchange-online-migration/ARC-001-EVAL-v1.0.md) [v2](https://tractorjuice.github.io/arckit-test-project-v2-hmrc-chatbot/#projects/001-hmrc-chatbot/ARC-001-EVAL-v1.0.md) [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-EVAL-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/ARC-002-EVAL-v1.0.md) [v3/003](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/003-peripherals-update-upgrade/ARC-003-EVAL-v1.0.md) [v3/005](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/005-cloud-pki/ARC-005-EVAL-v1.0.md) [v6](https://tractorjuice.github.io/arckit-test-project-v6-patent-system/#projects/001-patent-management-system-for-the-intellectual-property-office/ARC-001-EVAL-v1.0.md) | 🟢 Live |
  1295. | `/arckit:score` | Score vendor proposals with structured storage, side-by-side comparison, sensitivity analysis, and audit trail | — | 🔵 Beta |
  1296. ### Design & Architecture
  1297. | Command | Description | Examples | Status |
  1298. |---------|-------------|----------|--------|
  1299. | `/arckit:archify` | Render governed artefacts as interactive, self-contained HTML diagrams via Archify, or Wardley Maps via ArcKit's built-in renderer | — | 🧪 Experimental |
  1300. | `/arckit:diagram` | Generate architecture diagrams using Mermaid for visual documentation | [v1](https://tractorjuice.github.io/arckit-test-project-v1-m365/#projects/001-exchange-online-migration/diagrams/ARC-001-DIAG-001-v1.0.md) [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/diagrams/ARC-001-DIAG-001-v1.0.md) [v3/005](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/005-cloud-pki/diagrams/ARC-005-DIAG-001-v1.0.md) [v3/007](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/007-vpn-service-windows11-autopilot/diagrams/ARC-007-DIAG-001-v1.0.md) [v10](https://tractorjuice.github.io/arckit-test-project-v10-training-marketplace/#projects/001-ai-training-marketplace/diagrams/ARC-001-DIAG-001-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/diagrams/ARC-001-DIAG-001-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/diagrams/ARC-001-DIAG-001-v1.0.md) [v19](https://tractorjuice.github.io/arckit-test-project-v19-gov-api-aggregator/#projects/001-uk-government-api-aggregator/diagrams/ARC-001-DIAG-001-v1.0.md) | 🟢 Live |
  1301. | `/arckit:hld-review` | Review High-Level Design (HLD) against architecture principles and requirements | [v3](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/reviews/ARC-001-HLDR-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/reviews/ARC-001-HLDR-v1.0.md) | 🔵 Beta |
  1302. | `/arckit:dld-review` | Review Detailed Design (DLD) for implementation readiness | — | 🔵 Beta |
  1303. ### Operations
  1304. | Command | Description | Examples | Status |
  1305. |---------|-------------|----------|--------|
  1306. | `/arckit:backlog` | Generate prioritised product backlog from ArcKit artifacts - convert requirements to user stories, organise into sprints | [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-BKLG-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/ARC-002-BKLG-v1.0.md) [v3/003](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/003-peripherals-update-upgrade/ARC-003-BKLG-v1.0.md) [v3/004](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/004-conference-facilities-modernization/ARC-004-BKLG-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-BKLG-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-BKLG-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/ARC-001-BKLG-v1.0.md) [v19](https://tractorjuice.github.io/arckit-test-project-v19-gov-api-aggregator/#projects/001-uk-government-api-aggregator/ARC-001-BKLG-v1.0.md) | 🔵 Beta |
  1307. | `/arckit:trello` | Export product backlog to Trello - create board, lists, cards with labels and checklists from backlog JSON | — | 🟣 Experimental |
  1308. | `/arckit:servicenow` | Create comprehensive ServiceNow service design with CMDB, SLAs, incident management, and change control | [v3](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-SNOW-v1.0.md) | 🔵 Beta |
  1309. | `/arckit:devops` | Create DevOps strategy with CI/CD pipelines, IaC, container orchestration, and developer experience | [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-DEVOPS-v1.0.md) | 🟣 Experimental |
  1310. | `/arckit:mlops` | Create MLOps strategy with model lifecycle, training pipelines, serving, monitoring, and governance | [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-MLOPS-v1.0.md) | 🟣 Experimental |
  1311. | `/arckit:finops` | Create FinOps strategy with cloud cost management, optimization, governance, and forecasting | [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-FINOPS-v1.0.md) | 🟣 Experimental |
  1312. | `/arckit:operationalize` | Create operational readiness pack with support model, runbooks, DR/BCP, on-call, and handover documentation | [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-OPS-v1.0.md) | 🟣 Experimental |
  1313. | `/arckit:traceability` | Generate requirements traceability matrix from requirements to design to tests | [v1](https://tractorjuice.github.io/arckit-test-project-v1-m365/#projects/001-exchange-online-migration/ARC-001-TRAC-v1.0.md) [v2](https://tractorjuice.github.io/arckit-test-project-v2-hmrc-chatbot/#projects/001-hmrc-chatbot/ARC-001-TRAC-v1.0.md) [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-TRAC-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/ARC-002-TRAC-v1.0.md) [v3/003](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/003-peripherals-update-upgrade/ARC-003-TRAC-v1.0.md) [v6](https://tractorjuice.github.io/arckit-test-project-v6-patent-system/#projects/001-patent-management-system-for-the-intellectual-property-office/ARC-001-TRAC-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-TRAC-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-TRAC-v1.0.md) | 🟢 Live |
  1314. ### Quality & Governance
  1315. | Command | Description | Examples | Status |
  1316. |---------|-------------|----------|--------|
  1317. | `/arckit:analyze` | Perform comprehensive governance quality analysis across architecture artifacts | [v6](https://tractorjuice.github.io/arckit-test-project-v6-patent-system/#projects/001-patent-management-system-for-the-intellectual-property-office/ARC-001-ANAL-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-ANAL-v1.0.md) [v11](https://tractorjuice.github.io/arckit-test-project-v11-national-highways-data/#projects/001-national-highways-data-architecture-modernization/ARC-001-ANAL-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-ANAL-v1.0.md) | 🔵 Beta |
  1318. | `/arckit:principles-compliance` | Assess compliance with architecture principles and generate scorecard with evidence, gaps, and recommendations | [v3](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-PRIN-COMP-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-PRIN-COMP-v1.0.md) | 🟢 Live |
  1319. | `/arckit:story` | Generate comprehensive project story with timeline analysis, traceability, and governance achievements | [v3](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-STORY-v1.0.md) [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/#projects/001-ons-data-platform-modernisation/ARC-001-STORY-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-STORY-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-STORY-v1.0.md) | 🟢 Live |
  1320. | `/arckit:presentation` | Generate MARP slide deck from project artifacts for governance boards and stakeholder briefings | — | 🔵 Beta |
  1321. | `/arckit:conformance` | Assess architecture conformance — ADR decision implementation, cross-decision consistency, architecture drift, technical debt, and custom constraint rules | — | 🔵 Beta |
  1322. | `/arckit:health` | Scan projects for stale research, forgotten ADRs, unresolved review conditions, orphaned requirements, missing traceability, and version drift | — | 🔵 Beta |
  1323. | `/arckit:impact` | Analyse blast radius of changes — reverse dependency tracing | — | 🟣 Experimental |
  1324. | `/arckit:search` | Search across all project artifacts by keyword, document type, or requirement ID | — | 🔵 Beta |
  1325. | `/arckit:navigator` | Project-level GPS — show coverage against the essential ArcKit baseline, surface DRAFT/stale/orphan artifacts, and recommend the next slash command to run | — | 🟢 Live |
  1326. | `/arckit:graph-report` | Governance metrics dashboard — coverage by category, cross-reference density, compliance readiness, and project comparison across all working projects | — | 🟢 Live |
  1327. | `/arckit:customize` | Copy templates to `.arckit/templates-custom/` for customization (preserved across updates) | — | 🟢 Live |
  1328. | `/arckit:maturity-model` | Generate capability maturity model with current-state assessment, target-state definition, and improvement roadmap | — | 🔵 Beta |
  1329. | `/arckit:template-builder` | Create new document templates through interactive interview — generates community-origin templates, guides, and optional shareable bundles | — | 🟠 Alpha |
  1330. ### UK Government
  1331. | Command | Description | Examples | Status |
  1332. |---------|-------------|----------|--------|
  1333. | `/arckit:service-assessment` | Prepare for [GDS Service Standard](https://www.gov.uk/service-manual/service-assessments) assessment - analyze evidence against 14 points, identify gaps, generate readiness report | [v16](https://tractorjuice.github.io/arckit-test-project-v16-doctors-appointment/#projects/001-doctors-appointment/ARC-001-SASS-v1.0.md) | 🔵 Beta |
  1334. | `/arckit:tcop` | Generate a [Technology Code of Practice (TCoP)](https://www.gov.uk/guidance/the-technology-code-of-practice) review document for a UK Government technology project | [v6](https://tractorjuice.github.io/arckit-test-project-v6-patent-system/#projects/001-patent-management-system-for-the-intellectual-property-office/ARC-001-TCOP-v1.0.md) [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/#projects/001-ons-data-platform-modernisation/ARC-001-TCOP-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-TCOP-v1.0.md) [v11](https://tractorjuice.github.io/arckit-test-project-v11-national-highways-data/#projects/001-national-highways-data-architecture-modernization/ARC-001-TCOP-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-TCOP-v1.0.md) | 🔵 Beta |
  1335. | `/arckit:secure` | Generate a Secure by Design assessment for UK Government projects (civilian departments) | [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/#projects/001-ons-data-platform-modernisation/ARC-001-SECD-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-SECD-v1.0.md) [v11](https://tractorjuice.github.io/arckit-test-project-v11-national-highways-data/#projects/001-national-highways-data-architecture-modernization/ARC-001-SECD-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-SECD-v1.0.md) [v16](https://tractorjuice.github.io/arckit-test-project-v16-doctors-appointment/#projects/001-doctors-appointment/ARC-001-SECD-v1.0.md) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/#projects/001-uk-fuel-price-transparency-service/ARC-001-SECD-v1.0.md) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/#projects/001-smart-meter-app/ARC-001-SECD-v1.0.md) [v19](https://tractorjuice.github.io/arckit-test-project-v19-gov-api-aggregator/#projects/001-uk-government-api-aggregator/ARC-001-SECD-v1.0.md) | 🔵 Beta |
  1336. | `/arckit:ai-playbook` | Assess [UK Government AI Playbook](https://www.gov.uk/government/publications/ai-playbook-for-the-uk-government) compliance for responsible AI deployment | [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-AIPB-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-AIPB-v1.0.md) | 🟠 Alpha |
  1337. | `/arckit:atrs` | Generate [Algorithmic Transparency Recording Standard (ATRS)](https://www.gov.uk/government/collections/algorithmic-transparency-recording-standard-hub) record for AI/algorithmic tools | [v2](https://tractorjuice.github.io/arckit-test-project-v2-hmrc-chatbot/#projects/001-hmrc-chatbot/ARC-001-ATRS-v1.0.md) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/#projects/001-cabinet-office-genai/ARC-001-ATRS-v1.0.md) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/#projects/001-scts-genai-programme/ARC-001-ATRS-v1.0.md) | 🟠 Alpha |
  1338. ### UK MOD
  1339. | Command | Description | Examples | Status |
  1340. |---------|-------------|----------|--------|
  1341. | `/arckit:mod-secure` | Generate a MOD Secure by Design assessment for UK Ministry of Defence projects using CAAT and continuous assurance | [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-SECD-MOD-v1.0.md) [v3/006](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/006-large-format-printer/ARC-006-SECD-MOD-v1.0.md) | 🟣 Experimental |
  1342. | `/arckit:jsp-936` | Generate [MOD JSP 936](https://www.gov.uk/government/publications/jsp-936-dependable-artificial-intelligence-ai-in-defence-part-1-directive) AI assurance documentation for defence AI/ML systems | — | 🟣 Experimental |
  1343. ### Documentation & Publishing
  1344. | Command | Description | Examples | Status |
  1345. |---------|-------------|----------|--------|
  1346. | `/arckit:glossary` | Generate comprehensive project glossary with terms, definitions, acronyms, and cross-references | — | 🔵 Beta |
  1347. | `/arckit:pages` | Generate documentation site with Mermaid diagram support | [v1](https://tractorjuice.github.io/arckit-test-project-v1-m365/) [v2](https://tractorjuice.github.io/arckit-test-project-v2-hmrc-chatbot/) [v3](https://tractorjuice.github.io/arckit-test-project-v3-windows11/) [v6](https://tractorjuice.github.io/arckit-test-project-v6-patent-system/) [v7](https://tractorjuice.github.io/arckit-test-project-v7-nhs-appointment/) [v8](https://tractorjuice.github.io/arckit-test-project-v8-ons-data-platform/) [v9](https://tractorjuice.github.io/arckit-test-project-v9-cabinet-office-genai/) [v10](https://tractorjuice.github.io/arckit-test-project-v10-training-marketplace/) [v11](https://tractorjuice.github.io/arckit-test-project-v11-national-highways-data/) [v14](https://tractorjuice.github.io/arckit-test-project-v14-scottish-courts/) [v16](https://tractorjuice.github.io/arckit-test-project-v16-doctors-appointment/) [v17](https://tractorjuice.github.io/arckit-test-project-v17-fuel-prices/) [v18](https://tractorjuice.github.io/arckit-test-project-v18-smart-meter/) [v19](https://tractorjuice.github.io/arckit-test-project-v19-gov-api-aggregator/) | 🟠 Alpha |
  1348. ---
  1349. ## Wardley Mapping for Strategic Architecture
  1350. ArcKit uses Wardley Maps to expose the strategic position of every component before you commit to a solution. The `/arckit:wardley` command produces ready-to-visualise maps that:
  1351. - Trace user needs through the supporting value chain so gaps and duplicated effort are obvious.
  1352. - Plot evolution from Genesis → Commodity to reveal when to build, buy, reuse, or retire capabilities.
  1353. - Feed procurement, vendor evaluation, and design reviews with shared situational awareness.
  1354. Maps are emitted in the Open Wardley Map format — paste them straight into [https://create.wardleymaps.ai](https://create.wardleymaps.ai) for a visual view. Full example outputs live in the public demos such as `arckit-test-project-v3-windows11` (enterprise OS rollout strategy) and `arckit-test-project-v14-scottish-courts` (GenAI platform strategy).
  1355. ---
  1356. ## Architecture Diagrams with Mermaid
  1357. **ArcKit generates visual architecture diagrams using Mermaid for clear technical communication.**
  1358. ### What are Architecture Diagrams?
  1359. Architecture diagrams visualize system structure, interactions, and deployment for:
  1360. - **Technical Communication**: Share architecture with stakeholders
  1361. - **Design Documentation**: Document current and future state
  1362. - **Vendor Evaluation**: Compare vendor technical approaches
  1363. - **UK Government Compliance**: Visualize Cloud First, GOV.UK services, PII handling
  1364. ### Diagram Types
  1365. ArcKit supports 6 essential diagram types based on the C4 Model and enterprise architecture best practices:
  1366. | Diagram Type | Level | Purpose | When to Use |
  1367. |--------------|-------|---------|-------------|
  1368. | **C4 Context** | Level 1 | System in context with users and external systems | After requirements, to show system boundaries |
  1369. | **C4 Container** | Level 2 | Technical containers and technology choices | After HLD, for vendor review |
  1370. | **C4 Component** | Level 3 | Internal components within a container | After DLD, for implementation |
  1371. | **Deployment** | Infrastructure | Cloud resources and network topology | Cloud First compliance, cost estimation |
  1372. | **Sequence** | Interaction | API flows and request/response patterns | Integration requirements, API design |
  1373. | **Data Flow** | Data | How data moves, PII handling, GDPR compliance | UK GDPR, DPIA requirements |
  1374. Use `/arckit:diagram` directly, or supply an explicit type such as `context`, `container`, `sequence`, or `dataflow`. Outputs bundle component inventories with Wardley evolution tags, built-in GOV.UK compliance scaffolding (Notify, Pay, Design System), Cloud First network patterns, GDPR annotations, and traceability back to requirements and tests. For full examples, browse the diagram folders in `arckit-test-project-v3-windows11` and `arckit-test-project-v14-scottish-courts`.
  1375. ## ServiceNow Service Management Design
  1376. ArcKit turns architecture artefacts into an operations-ready ServiceNow pack. The `/arckit:servicenow` command builds:
  1377. - CMDB hierarchies, SLAs, and change risk straight from requirements, diagrams, and Wardley Maps.
  1378. - ITIL-aligned runbooks covering incident, change, monitoring, and transition activities.
  1379. - UK government extras such as GDS Service Standard, Technology Code of Practice, and GOV.UK Pay/Notify dependencies when relevant.
  1380. For full outputs, explore the public demos (for example `arckit-test-project-v3-windows11`) where the generated ServiceNow design files and checklists are published end-to-end.
  1381. ---
  1382. ## Documentation
  1383. Key references live in `docs/` and top-level guides:
  1384. - Quick tour: [docs/index.html](docs/index.html) mirrors the public landing page.
  1385. - Lifecycle visuals: [WORKFLOW-DIAGRAMS.md](docs/WORKFLOW-DIAGRAMS.md) and [DEPENDENCY-MATRIX.md](docs/DEPENDENCY-MATRIX.md) cover command flow and relationships.
  1386. - Core guides: [docs/guides/principles.md](docs/guides/principles.md), [docs/guides/requirements.md](docs/guides/requirements.md), [docs/guides/procurement.md](docs/guides/procurement.md), [docs/guides/design-review.md](docs/guides/design-review.md).
  1387. - Traceability: [docs/guides/traceability.md](docs/guides/traceability.md) documents end-to-end coverage patterns.
  1388. - **DDaT Role Guides**: [docs/guides/roles/](docs/guides/roles/) — 18 guides mapping ArcKit commands to [UK Government DDaT Capability Framework](https://ddat-capability-framework.service.gov.uk/) roles (Enterprise Architect, Solution Architect, Product Manager, etc.).
  1389. ---
  1390. ## Comparison to Other Tools
  1391. Every tool here now has AI features. Sparx has Kernaro AI and an MCP server, Ardoq relaunched as AI-first in May 2026, LeanIX ships an AI assistant and an MCP server, and Confluence has Atlassian Rovo. The difference is what the AI works on. The EA platforms apply it to the application inventory: what exists and how it connects. ArcKit applies it to the governance evidence: the documents an assessment, a design authority or a procurement asks for. They work well together, since ArcKit can read an export from your EA repository as source material.
  1392. | Feature | ArcKit | Sparx EA | Ardoq | LeanIX | Confluence |
  1393. |---------|--------|----------|-------|--------|------------|
  1394. | **AI features** | ✅ Governance documents | ✅ Models | ✅ Inventory | ✅ Inventory | ✅ Pages |
  1395. | **UK assessment templates** (TCoP, Service Standard, Secure by Design, Green Book) | ✅ | ❌ | ❌ | ❌ | ❌ |
  1396. | **Citations and provenance on AI output** | ✅ | ❌ Not claimed | ❌ Not claimed | ❌ Not claimed | ❌ Not claimed |
  1397. | **Wardley Mapping** | ✅ | ❌ | ⚠️ Limited | ❌ | ❌ |
  1398. | **Artefacts versioned in your own git repo** | ✅ | ⚠️ Via integration | ❌ | ❌ | ❌ |
  1399. | **Vendor RFP and G-Cloud/DOS** | ✅ | ❌ | ❌ | ❌ | ⚠️ Manual |
  1400. | **Application inventory and dependency modelling** | ❌ Use an EA tool | ✅ | ✅ | ✅ | ❌ |
  1401. | **Cost to start** | Free (MIT) | $$$$ | $$$$ | $$$$ | $$ |
  1402. ---
  1403. ## Requirements
  1404. - **Python 3.11+**
  1405. - **Node.js** on your `PATH`. ArcKit's hooks and helper scripts need it, and without it ArcKit artefacts can't be written
  1406. - **Git** (optional but recommended)
  1407. - **AI Coding Agent**: [Claude Code](https://www.anthropic.com/claude-code) v2.1.319+ (via plugin), [Gemini CLI](https://github.com/google-gemini/gemini-cli) (via extension), [OpenCode CLI](https://opencode.net/cli) (via CLI), or [OpenAI Codex CLI](https://chatgpt.com/features/codex) (via CLI)
  1408. - **uv** for package management: [Install uv](https://docs.astral.sh/uv/)
  1409. ---
  1410. ## Installation from Source
  1411. ```bash
  1412. # Clone the repository
  1413. git clone https://github.com/tractorjuice/arc-kit.git
  1414. cd arc-kit
  1415. # Install in development mode
  1416. pip install -e .
  1417. # Run the CLI
  1418. arckit init my-project
  1419. ```
  1420. ---
  1421. ## Documentation
  1422. Full guidance lives in `docs/` and the static site.
  1423. - Quick tour: [docs/index.html](docs/index.html) (mirrors the public landing page).
  1424. - Core guides: [docs/guides/principles.md](docs/guides/principles.md), [docs/guides/requirements.md](docs/guides/requirements.md), [docs/guides/procurement.md](docs/guides/procurement.md), [docs/guides/design-review.md](docs/guides/design-review.md).
  1425. - Reference packs: [WORKFLOW-DIAGRAMS.md](docs/WORKFLOW-DIAGRAMS.md) and [DEPENDENCY-MATRIX.md](docs/DEPENDENCY-MATRIX.md) cover lifecycle visualisations and the command dependency matrix.
  1426. - Traceability: [docs/guides/traceability.md](docs/guides/traceability.md) documents end-to-end requirements coverage.
  1427. ## Relationship to Spec Kit
  1428. ArcKit is inspired by [Spec Kit](https://github.com/github/spec-kit) but targets a different audience:
  1429. | | Spec Kit | ArcKit |
  1430. |---|----------|--------|
  1431. | **Audience** | Product Managers, Developers | Enterprise Architects, Procurement |
  1432. | **Focus** | Feature development (0→1 code generation) | Architecture governance & vendor management |
  1433. | **Workflow** | Spec → Plan → Tasks → Code | Requirements → RFP → Design Review → Traceability |
  1434. | **Output** | Working code | Architecture documentation & governance |

Lines 2,001–2,137 are not shown. The link to the file on GitHub has every line.

plugins/arckit-claude/scripts/validate-handoff.mjs · Bundled script · 457 lines · 1 finding marked
  1. #!/usr/bin/env node
  2. /**
  3. * Validate a JSON payload against a JSON Schema 2020-12 file.
  4. *
  5. * Usage: node validate-handoff.mjs <schema.json> <payload.json>
  6. *
  7. * Exit 0 on success: prints the sanitised, validated payload as JSON on stdout.
  8. * Exit 1 on failure: prints {ok:false, errors:[{path,msg}]} on stdout.
  9. *
  10. * Before schema validation every string leaf (and every object key) is
  11. * passed through a sanitiser, because the payload is a reader's summary
  12. * of untrusted text — vendor pages, MCP results, repository READMEs —
  13. * and the orchestrator and writer read the validator's stdout as data:
  14. *
  15. * - NFKC-normalised, so a full-width or compatibility homoglyph cannot
  16. * slip past an enum or pattern check that its ASCII form would fail;
  17. * - invisible and format characters (zero-width joiners, bidi
  18. * overrides, soft hyphens, BOM, variation selectors) are removed and
  19. * C0/C1 control characters other than tab and newline become spaces.
  20. * These carry no meaning in a summary and are the usual carriers of
  21. * hidden instructions.
  22. *
  23. * Three shapes are rejected rather than repaired, because each is
  24. * evidence that source text is trying to be read as conversation rather
  25. * than as data, and the reader's single re-dispatch should see it named:
  26. *
  27. * - Unicode tag characters (U+E0000–U+E007F), which spell invisible
  28. * ASCII;
  29. * - transcript-shaped tags — <tool_result>, <function_calls>, <system>,
    • Note: Usual in code (tag names in paths and patterns): Contains a <system> block, a common wrapper for instructions hidden in a tool description
    • Line 29 on GitHub
  30. * <human>, <assistant>, <system-reminder>, their namespaced and
  31. * closing forms — and <|...|> special tokens;
  32. * - a forged turn marker: a role word and a colon at the start of a
  33. * string or after a blank line ("\n\nassistant:").
  34. *
  35. * The pattern set follows the fence sanitiser in Anthropic's
  36. * commerce-agents reference (commerce_common/fencing.py); every regex is
  37. * bounded so it stays linear on hostile input.
  38. *
  39. * Used by arckit-claude/agents/arckit-datascout.md (the orchestrator)
  40. * to validate output from arckit-datascout-reader before scoring.
  41. *
  42. * Implementation note: pure Node, zero npm dependencies. The plugin
  43. * marketplace clones the repo but does not run `npm install`, so any
  44. * runtime dep would force every end user to install dependencies in
  45. * the plugin cache before ArcKit could validate a handoff. The supported
  46. * JSON Schema feature set below is exactly what
  47. * datascout-handoff.schema.json uses; new keywords need explicit support
  48. * added here.
  49. *
  50. * Supported keywords:
  51. * - type (object, array, string, integer, number, boolean, null)
  52. * - required, properties, additionalProperties: false
  53. * - items (with $ref)
  54. * - enum
  55. * - pattern, maxLength, minLength
  56. * - format: uri, date-time
  57. * - maxItems, minItems
  58. * - minimum, maximum
  59. * - $ref ("#/$defs/<name>" form only)
  60. *
  61. * Unsupported keywords are silently ignored; the schema's $schema, $id,
  62. * title, description fields are documentation only.
  63. */
  64. import { readFileSync } from 'node:fs';
  65. import { resolve } from 'node:path';
  66. import { fileURLToPath } from 'node:url';
  67. // ── Sanitiser ──────────────────────────────────────────────────────────
  68. // Zero-width, bidi, and format controls; removed silently. The tag block
  69. // (U+E0000–U+E007F) is deliberately absent — see TAG_CHARS below.
  70. const INVISIBLE_RANGES = [
  71. [0x00ad, 0x00ad], // soft hyphen
  72. [0x061c, 0x061c], // Arabic letter mark
  73. [0x180e, 0x180e], // Mongolian vowel separator
  74. [0x200b, 0x200f], // zero-width space/joiners, LRM/RLM
  75. [0x2028, 0x2029], // line/paragraph separators
  76. [0x202a, 0x202e], // bidi embedding/overrides
  77. [0x2060, 0x2064], // word joiner, invisible operators
  78. [0x2066, 0x2069], // bidi isolates
  79. [0x206a, 0x206f], // deprecated format controls
  80. [0xfe00, 0xfe0f], // variation selectors
  81. [0xfeff, 0xfeff], // byte-order mark / zero-width no-break space
  82. [0xfff9, 0xfffb], // interlinear annotation controls
  83. [0xe0100, 0xe01ef], // variation selectors supplement
  84. ];
  85. const INVISIBLE = new RegExp(
  86. '[' + INVISIBLE_RANGES.map(([lo, hi]) => `\\u{${lo.toString(16)}}-\\u{${hi.toString(16)}}`).join('') + ']',
  87. 'gu',
  88. );
  89. // Tag characters spell invisible ASCII — an instruction the model can read
  90. // and a human cannot see. Rejected, not stripped.
  91. const TAG_CHARS = /[\u{E0000}-\u{E007F}]/u;
  92. const TAG_CHARS_ALL = /[\u{E0000}-\u{E007F}]/gu;
  93. // C0/C1 control characters except tab and newline; replaced with a space.
  94. const CONTROL = /[\x00-\x08\x0b\x0c\x0e-\x1f\x7f-\x9f]/g;
  95. // Transcript and tool-call markup, optionally namespaced ("ns:invoke").
  96. // Only tag-shaped text matches — bare, closing, or with name="value"
  97. // attributes — so prose such as "<system requirements>" passes; `parameter`
  98. // and `result` count only when namespaced. Quantifiers are bounded and
  99. // non-adjacent, which keeps this linear on unclosed input.
  100. const TAG_ATTRS =
  101. '(?:[ \\t]+[\\w:.-]{1,40}[ \\t]*=[ \\t]*(?:"[^"]{0,200}"|\'[^\']{0,200}\'|[^\\s"\'>]{1,200})){0,8}';
  102. const SPECIAL_TOKEN = new RegExp(
  103. '<[ \\t]*/?[ \\t]*(?:' +
  104. '(?:[a-z][\\w.-]{0,30}:)?(?:transcript|conversation|function_calls|function_results' +
  105. '|invoke|tool_use|tool_result|system-reminder|system|human|user|assistant)' +
  106. '|[a-z][\\w.-]{0,30}:(?:parameter|result)' +
  107. ')\\b' + TAG_ATTRS + '[ \\t]*/?>' +
  108. '|<\\|[^|<>\\r\\n]{1,64}\\|>',
  109. 'i',
  110. );
  111. // A forged turn boundary: a role word and a colon at the start of the
  112. // string or after a blank line. Mid-sentence role words, single-newline
  113. // headings, and one-letter list markers ("A:") do not match.
  114. const TURN_INDICATOR = /(?:^|(?:\r\n|\r|\n)[ \t]*(?:\r\n|\r|\n))[ \t]*(?:human|assistant|system|user)[ \t]*:/i;
  115. function sanitizeText(text, path, errors) {
  116. if (TAG_CHARS.test(text)) {
  117. errors.push({ path: pathOrRoot(path), msg: 'contains Unicode tag characters (invisible ASCII); source text must be summarised, not copied' });
  118. }
  119. text = text.normalize('NFKC').replace(INVISIBLE, '').replace(CONTROL, ' ');
  120. const token = SPECIAL_TOKEN.exec(text);
  121. if (token) {
  122. errors.push({ path: pathOrRoot(path), msg: 'contains transcript-shaped markup (a tag such as <system> or <tool_result>, or a <|...|> token); it is data, not conversation — remove it' });
  123. }
  124. const turn = TURN_INDICATOR.exec(text);
  125. if (turn) {
  126. errors.push({ path: pathOrRoot(path), msg: 'contains a forged turn marker (a role word and a colon opening the text or following a blank line); remove it' });
  127. }
  128. return text;
  129. }
  130. function sanitize(value, path, errors) {
  131. if (typeof value === 'string') return sanitizeText(value, path, errors);
  132. if (Array.isArray(value)) return value.map((v, i) => sanitize(v, `${path}/${i}`, errors));
  133. if (value !== null && typeof value === 'object') {
  134. const out = {};
  135. for (const [k, v] of Object.entries(value)) {
  136. // Errors about a key are reported at its sanitised path, so the raw
  137. // key's invisible characters never reach an error message.
  138. const keyErrors = [];
  139. const key = sanitizeText(k, '', keyErrors);
  140. // "/" and "~" are escaped as in a JSON pointer, so a key holding a
  141. // slash stays one path segment.
  142. // An empty key would read as its parent's path, so it gets a name no
  143. // schema defines.
  144. const segment = key.replace(TAG_CHARS_ALL, '').replace(/~/g, '~0').replace(/\//g, '~1');
  145. const keyPath = `${path}/${segment === '' ? '(empty key)' : segment}`;
  146. for (const e of keyErrors) errors.push({ ...e, path: keyPath });
  147. out[key] = sanitize(v, keyPath, errors);
  148. }
  149. return out;
  150. }
  151. return value;
  152. }
  153. /**
  154. * Sanitise then validate `payload` against `schema`. Returns
  155. * `{ ok: true, payload }` with the sanitised payload, or
  156. * `{ ok: false, errors: [{path, msg}] }`. Pure: no I/O, no process exit.
  157. * Exported for hooks/validate-reader-handoff.mjs, which validates reader
  158. * subagent output without a Bash call.
  159. */
  160. export function checkHandoff(schema, rawPayload) {
  161. const errors = [];
  162. const payload = sanitize(rawPayload, '', errors);
  163. if (errors.length === 0) {
  164. validate(payload, schema, '', schema, errors);
  165. }
  166. return errors.length === 0 ? { ok: true, payload } : { ok: false, errors: reportable(errors, schema) };
  167. }
  168. // ── Error reporting ────────────────────────────────────────────────────
  169. // An error is read by the orchestrator, which holds Write, Edit and Bash, so
  170. // it must carry nothing the payload's author chose. Messages never quote a
  171. // value. A path is built from the payload's own keys, so it is walked against
  172. // the schema: a segment is kept only while it is a property the schema
  173. // defines at that position, or an index into an array the schema defines
  174. // there. The first segment that is neither is shown as UNKNOWN_KEY and the
  175. // path stops. Identical lines are reported once.
  176. export const UNKNOWN_KEY = '(unknown key)';
  177. function safePath(path, schema) {
  178. if (path === '/' || path === '') return '/';
  179. const out = [];
  180. let node = schema;
  181. for (const raw of path.split('/').slice(1)) {
  182. const seg = decodeJsonPointer(raw);
  183. if (node && node.$ref) node = resolveRef(node.$ref, schema);
  184. if (node && node.properties && Object.hasOwn(node.properties, seg)) {
  185. out.push(seg);
  186. node = node.properties[seg];
  187. } else if (node && node.items && /^\d{1,6}$/.test(seg)) {
  188. out.push(seg);
  189. node = node.items;
  190. } else {
  191. out.push(UNKNOWN_KEY);
  192. break;
  193. }
  194. }
  195. return `/${out.join('/')}`;
  196. }
  197. function reportable(errors, schema) {
  198. const seen = new Set();
  199. const out = [];
  200. for (const e of errors) {
  201. const path = safePath(e.path, schema);
  202. const line = `${path}\u0000${e.msg}`;
  203. if (seen.has(line)) continue;
  204. seen.add(line);
  205. out.push({ path, msg: e.msg });
  206. }
  207. return out;
  208. }
  209. function main(argv) {
  210. const [, , schemaPath, payloadPath] = argv;
  211. if (!schemaPath || !payloadPath) {
  212. emitErrors([{ path: '/', msg: 'Usage: validate-handoff.mjs <schema.json> <payload.json>' }]);
  213. process.exit(1);
  214. }
  215. let schema, payload;
  216. try {
  217. schema = JSON.parse(readFileSync(schemaPath, 'utf8'));
  218. } catch (e) {
  219. emitErrors([{ path: '/', msg: `failed to read schema: ${e.message}` }]);
  220. process.exit(1);
  221. }
  222. try {
  223. payload = JSON.parse(readFileSync(payloadPath, 'utf8'));
  224. } catch (e) {
  225. // Not e.message: a JSON parse error quotes the text around the fault.
  226. emitErrors([{ path: '/', msg: `failed to read payload: ${e instanceof SyntaxError ? 'it is not valid JSON' : 'the file could not be read'}` }]);
  227. process.exit(1);
  228. }
  229. const result = checkHandoff(schema, payload);
  230. if (result.ok) {
  231. console.log(JSON.stringify(result.payload));
  232. process.exit(0);
  233. }
  234. emitErrors(result.errors);
  235. process.exit(1);
  236. }
  237. // Run as a CLI only when executed directly, not when imported.
  238. if (process.argv[1] && resolve(process.argv[1]) === fileURLToPath(import.meta.url)) {
  239. main(process.argv);
  240. }
  241. // ── Validator core ────────────────────────────────────────────────────
  242. function validate(value, schemaNode, path, root, errors) {
  243. if (schemaNode == null) return;
  244. // Resolve $ref before doing anything else.
  245. if (schemaNode.$ref) {
  246. const resolved = resolveRef(schemaNode.$ref, root);
  247. if (!resolved) {
  248. errors.push({ path: pathOrRoot(path), msg: `cannot resolve $ref: ${schemaNode.$ref}` });
  249. return;
  250. }
  251. return validate(value, resolved, path, root, errors);
  252. }
  253. // type check
  254. if (schemaNode.type) {
  255. const actualType = jsonType(value);
  256. const expected = schemaNode.type;
  257. const ok = Array.isArray(expected)
  258. ? expected.some(t => typeMatches(t, value, actualType))
  259. : typeMatches(expected, value, actualType);
  260. if (!ok) {
  261. errors.push({ path: pathOrRoot(path), msg: `must be ${formatType(expected)}, got ${actualType}` });
  262. return; // type mismatch invalidates downstream checks
  263. }
  264. }
  265. // enum
  266. if (schemaNode.enum) {
  267. if (!schemaNode.enum.some(allowed => deepEqual(allowed, value))) {
  268. errors.push({
  269. path: pathOrRoot(path),
  270. msg: `must be one of the ${schemaNode.enum.length} values the schema allows${allowedList(schemaNode.enum)}; the value given is not one of them`,
  271. });
  272. }
  273. }
  274. // string-specific
  275. if (typeof value === 'string') {
  276. if (schemaNode.minLength !== undefined && value.length < schemaNode.minLength) {
  277. errors.push({ path: pathOrRoot(path), msg: `string length ${value.length} below minLength ${schemaNode.minLength}` });
  278. }
  279. if (schemaNode.maxLength !== undefined && value.length > schemaNode.maxLength) {
  280. errors.push({ path: pathOrRoot(path), msg: `string length ${value.length} exceeds maxLength ${schemaNode.maxLength}` });
  281. }
  282. if (schemaNode.pattern) {
  283. let re;
  284. try { re = new RegExp(schemaNode.pattern); }
  285. catch (e) {
  286. errors.push({ path: pathOrRoot(path), msg: `schema pattern invalid: ${e.message}` });
  287. return;
  288. }
  289. if (!re.test(value)) {
  290. errors.push({ path: pathOrRoot(path), msg: `must match pattern ${schemaNode.pattern}` });
  291. }
  292. }
  293. if (schemaNode.format === 'uri' && !isLikelyUri(value)) {
  294. errors.push({ path: pathOrRoot(path), msg: 'must be valid URI' });
  295. }
  296. if (schemaNode.format === 'date-time' && !isIsoDateTime(value)) {
  297. errors.push({ path: pathOrRoot(path), msg: 'must be valid ISO 8601 date-time' });
  298. }
  299. }
  300. // numeric-specific
  301. if (typeof value === 'number') {
  302. if (schemaNode.minimum !== undefined && value < schemaNode.minimum) {
  303. errors.push({ path: pathOrRoot(path), msg: `must be >= ${schemaNode.minimum}` });
  304. }
  305. if (schemaNode.maximum !== undefined && value > schemaNode.maximum) {
  306. errors.push({ path: pathOrRoot(path), msg: `must be <= ${schemaNode.maximum}` });
  307. }
  308. }
  309. // array-specific
  310. if (Array.isArray(value)) {
  311. if (schemaNode.minItems !== undefined && value.length < schemaNode.minItems) {
  312. errors.push({ path: pathOrRoot(path), msg: `array length ${value.length} below minItems ${schemaNode.minItems}` });
  313. }
  314. if (schemaNode.maxItems !== undefined && value.length > schemaNode.maxItems) {
  315. errors.push({ path: pathOrRoot(path), msg: `array length ${value.length} exceeds maxItems ${schemaNode.maxItems}` });
  316. }
  317. if (schemaNode.items) {
  318. value.forEach((item, i) => validate(item, schemaNode.items, `${path}/${i}`, root, errors));
  319. }
  320. }
  321. // object-specific
  322. if (value !== null && typeof value === 'object' && !Array.isArray(value)) {
  323. if (schemaNode.required) {
  324. for (const key of schemaNode.required) {
  325. if (!(key in value)) {
  326. errors.push({ path: `${path}/${key}`, msg: 'required property missing' });
  327. }
  328. }
  329. }
  330. if (schemaNode.additionalProperties === false && schemaNode.properties) {
  331. // One line for the object, naming the schema's keys and not the payload's.
  332. const allowed = Object.keys(schemaNode.properties);
  333. const unknown = Object.keys(value).filter(key => !Object.hasOwn(schemaNode.properties, key)).length;
  334. if (unknown > 0) {
  335. errors.push({
  336. path: pathOrRoot(path),
  337. msg: `has ${unknown} unknown ${unknown === 1 ? 'property' : 'properties'} (additionalProperties: false); the keys the schema allows here are: ${allowed.join(', ')}`,
  338. });
  339. }
  340. }
  341. if (schemaNode.properties) {
  342. for (const [key, subschema] of Object.entries(schemaNode.properties)) {
  343. if (key in value) {
  344. validate(value[key], subschema, `${path}/${key}`, root, errors);
  345. }
  346. }
  347. }
  348. }
  349. }
  350. // ── Helpers ────────────────────────────────────────────────────────────
  351. function emitErrors(errs) {
  352. console.log(JSON.stringify({ ok: false, errors: errs }, null, 2));
  353. }
  354. /** The schema's own enum values, listed when they are short enough to help. */
  355. function allowedList(values) {
  356. if (!values.every(v => typeof v === 'string' || typeof v === 'number' || typeof v === 'boolean' || v === null)) return '';
  357. const list = values.map(v => JSON.stringify(v)).join(', ');
  358. return list.length <= 160 ? ` (${list})` : '';
  359. }
  360. function pathOrRoot(path) {
  361. return path === '' ? '/' : path;
  362. }
  363. function jsonType(value) {
  364. if (value === null) return 'null';
  365. if (Array.isArray(value)) return 'array';
  366. if (Number.isInteger(value)) return 'integer';
  367. return typeof value; // 'string' | 'number' | 'boolean' | 'object'
  368. }
  369. function typeMatches(expected, value, actualType) {
  370. if (expected === 'integer') return Number.isInteger(value);
  371. if (expected === 'number') return typeof value === 'number';
  372. return expected === actualType;
  373. }
  374. function formatType(t) {
  375. return Array.isArray(t) ? `one of [${t.join(', ')}]` : t;
  376. }
  377. function resolveRef(ref, root) {
  378. if (!ref.startsWith('#/')) return null;
  379. const parts = ref.slice(2).split('/').map(decodeJsonPointer);
  380. let node = root;
  381. for (const p of parts) {
  382. if (node == null || !(p in node)) return null;
  383. node = node[p];
  384. }
  385. return node;
  386. }
  387. function decodeJsonPointer(token) {
  388. return token.replace(/~1/g, '/').replace(/~0/g, '~');
  389. }
  390. function deepEqual(a, b) {
  391. if (a === b) return true;
  392. if (typeof a !== typeof b) return false;
  393. if (a === null || b === null) return a === b;
  394. if (Array.isArray(a)) {
  395. if (!Array.isArray(b) || a.length !== b.length) return false;
  396. return a.every((el, i) => deepEqual(el, b[i]));
  397. }
  398. if (typeof a === 'object') {
  399. const aKeys = Object.keys(a);
  400. const bKeys = Object.keys(b);
  401. if (aKeys.length !== bKeys.length) return false;
  402. return aKeys.every(k => deepEqual(a[k], b[k]));
  403. }
  404. return false;
  405. }
  406. function isLikelyUri(value) {
  407. // Permissive scheme + ":" + something (RFC 3986 absolute URI shape).
  408. // Permissive on purpose — the goal is to reject obvious non-URIs (free
  409. // text, missing scheme), not to fully validate every RFC corner case.
  410. return /^[A-Za-z][A-Za-z0-9+.-]*:\S+$/.test(value);
  411. }
  412. function isIsoDateTime(value) {
  413. // ISO 8601 UTC ("Z") or with offset ("+HH:MM" / "-HH:MM"). Permissive
  414. // on the fractional-seconds component.
  415. return /^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?(Z|[+-]\d{2}:?\d{2})$/.test(value);
  416. }

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.