Skip to content
Back to search

xiaolai

MarketplaceWorks with Claude CodeGitHubIncomplete

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/xiaolai--claude-plugin-marketplace/badge.svg)](/listings/xiaolai--claude-plugin-marketplace)

HTML

<a href="/listings/xiaolai--claude-plugin-marketplace"><img src="/api/listings/xiaolai--claude-plugin-marketplace/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

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

For Claude Code:

claude plugin marketplace add xiaolai/claude-plugin-marketplace

For Codex CLI:

codex plugin marketplace add xiaolai/claude-plugin-marketplace

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 · 480 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "xiaolai",
  3. "owner": {
  4. "name": "xiaolai"
  5. },
  6. "metadata": {
  7. "description": "Claude Code plugins by xiaolai"
  8. },
  9. "renames": {
  10. "cc-bridge": null,
  11. "codex-toolkit": null,
  12. "anthropic-docs": null,
  13. "mermaid-preview": null,
  14. "claude-english-buddy": "english-buddy",
  15. "dev-team": null
  16. },
  17. "plugins": [
  18. {
  19. "name": "cc-suite",
  20. "source": {
  21. "source": "github",
  22. "repo": "xiaolai/cc-suite"
  23. },
  24. "description": "One plugin to bridge and delegate across Claude Code, Codex CLI, and Antigravity — single-source AGENTS.md, shared skills, mirrored hooks and MCP servers, full Claude↔Codex bidirectional delegation (including Codex reading Claude's session history), a Claude→Grok Build delegation lane over ACP, a bounded read-only Claude→Qwen Code review lane (Safe Mode + Plan mode + sandbox, isolated target copies, verified tool boundary), project-scoped advisor agents, opt-in bridging to more coding agents (Grok Build, opencode, Qwen Code, Kimi CLI) via a tool-profile registry, never-stale model selection (the config records the 'latest' policy), a structured diagnostics engine (enabled-tools-aware health checks with verified auto-repair), and a cross-repo sweep that finds every project on the machine cc-suite has bridged and repairs bridge leftovers in one pass — dead MCP registrations, and skills symlinks left pointing at a pruned plugin version, which SessionStart now also re-points on its own. Supersedes cc-bridge and codex-toolkit.",
  25. "version": "2.5.0",
  26. "author": {
  27. "name": "xiaolai"
  28. },
  29. "repository": "https://github.com/xiaolai/cc-suite",
  30. "license": "ISC",
  31. "keywords": [
  32. "codex",
  33. "gemini",
  34. "agents-md",
  35. "mcp",
  36. "bridge",
  37. "delegation",
  38. "multi-tool",
  39. "audit",
  40. "code-review"
  41. ],
  42. "category": "developer-tools"
  43. },
  44. {
  45. "name": "tdd-guardian",
  46. "source": {
  47. "source": "github",
  48. "repo": "xiaolai/tdd-guardian-for-claude"
  49. },
  50. "description": "Enforces strict TDD discipline across unit/integration/e2e/contract lanes — specification-strength levels S1-S6 with property tooling, adversarial spec review before implementation, red receipts proving spec/implementation separation, per-path critical thresholds, 9-format coverage merging, and mutation testing",
  51. "version": "0.10.2",
  52. "author": {
  53. "name": "xiaolai"
  54. },
  55. "repository": "https://github.com/xiaolai/tdd-guardian-for-claude",
  56. "license": "ISC",
  57. "keywords": [
  58. "tdd",
  59. "testing",
  60. "coverage",
  61. "mutation-testing",
  62. "code-quality",
  63. "e2e",
  64. "integration-testing",
  65. "property-testing",
  66. "invariants"
  67. ],
  68. "category": "developer-tools"
  69. },
  70. {
  71. "name": "echo-sleuth",
  72. "source": {
  73. "source": "github",
  74. "repo": "xiaolai/echo-sleuth-for-claude"
  75. },
  76. "description": "Mine past Claude Code conversations for values, decisions, mistakes, patterns, and wisdom. Manage memory lifecycle: audit staleness, extract knowledge, prune waste.",
  77. "version": "0.4.4",
  78. "author": {
  79. "name": "xiaolai"
  80. },
  81. "repository": "https://github.com/xiaolai/echo-sleuth-for-claude",
  82. "license": "ISC",
  83. "keywords": [
  84. "conversation-history",
  85. "session-recall",
  86. "experience-mining",
  87. "git-history",
  88. "decision-archaeology"
  89. ],
  90. "category": "developer-tools"
  91. },
  92. {
  93. "name": "loc-guardian",
  94. "source": {
  95. "source": "github",
  96. "repo": "xiaolai/loc-guardian-for-claude"
  97. },
  98. "description": "Enforce per-file pure LOC limits — deterministic tokei-based counting, per-file ceilings and exemptions for files that are one thing by design, opus-powered extraction plans measured in pure LOC, and a --check mode that exits non-zero for CI and pre-commit hooks",
  99. "version": "0.4.2",
  100. "author": {
  101. "name": "xiaolai"
  102. },
  103. "repository": "https://github.com/xiaolai/loc-guardian-for-claude",
  104. "license": "ISC",
  105. "keywords": [
  106. "loc",
  107. "lines-of-code",
  108. "metrics",
  109. "tokei",
  110. "code-quality",
  111. "file-size-limits"
  112. ],
  113. "category": "developer-tools"
  114. },
  115. {
  116. "name": "grill",
  117. "source": {
  118. "source": "github",
  119. "repo": "xiaolai/grill-for-claude"
  120. },
  121. "description": "Deep codebase interrogation: a bounded three-finding quick review by default, with explicit full multi-agent reviews, five review styles and eight pressure tests.",
  122. "version": "1.4.0",
  123. "author": {
  124. "name": "xiaolai"
  125. },
  126. "repository": "https://github.com/xiaolai/grill-for-claude",
  127. "license": "ISC",
  128. "keywords": [
  129. "code-review",
  130. "architecture",
  131. "interrogation",
  132. "audit",
  133. "codebase-analysis"
  134. ],
  135. "category": "developer-tools"
  136. },
  137. {
  138. "name": "reason-grill",
  139. "source": {
  140. "source": "github",
  141. "repo": "xiaolai/reason-grill-for-claude"
  142. },
  143. "description": "Deep argument interrogation: a bounded quick review by default, with an explicit full adversarial panel and evidence-grounded verdicts.",
  144. "version": "0.4.0",
  145. "author": {
  146. "name": "xiaolai"
  147. },
  148. "repository": "https://github.com/xiaolai/reason-grill-for-claude",
  149. "license": "ISC",
  150. "keywords": [
  151. "argument-analysis",
  152. "critical-thinking",
  153. "reasoning",
  154. "steelman",
  155. "logic"
  156. ],
  157. "category": "developer-tools"
  158. },
  159. {
  160. "name": "docs-guardian",
  161. "source": {
  162. "source": "github",
  163. "repo": "xiaolai/docs-guardian-for-claude"
  164. },
  165. "description": "Documentation freshness, accuracy and coverage checks, plus commit and push guards that resolve the target repository and map outgoing source changes to documentation.",
  166. "version": "0.3.0",
  167. "author": {
  168. "name": "xiaolai"
  169. },
  170. "repository": "https://github.com/xiaolai/docs-guardian-for-claude",
  171. "license": "ISC",
  172. "keywords": [
  173. "documentation",
  174. "docs",
  175. "staleness",
  176. "coverage",
  177. "quality",
  178. "freshness"
  179. ],
  180. "category": "developer-tools"
  181. },
  182. {
  183. "name": "nlpm",
  184. "source": {
  185. "source": "github",
  186. "repo": "xiaolai/nlpm"
  187. },
  188. "description": "Natural-Language Programming Manager — score, check, fix, and test NL artifacts across Claude Code, Codex CLI, and Antigravity. Tier-aware scoring with per-tool overlays. v1.0.0 marks the multi-tool branded release: nlpm:conventions splits into universal floor + per-tool overlays (conventions-claude, conventions-codex, conventions-antigravity); the scoring rubric splits Hooks per tool (the three event vocabularies are not 1:1 mappable); new artifact rows for .codex-plugin/plugin.json, .agents/plugins/marketplace.json, agents/openai.yaml sidecars, gemini-extension.json, LSP, monitors. Standalone Python validator (bin/nlpm-check) remains tool-agnostic and Claude-Code-free for pre-commit hooks and CI.",
  189. "version": "1.4.3",
  190. "author": {
  191. "name": "xiaolai"
  192. },
  193. "repository": "https://github.com/xiaolai/nlpm",
  194. "license": "ISC",
  195. "keywords": [
  196. "nlp",
  197. "lint",
  198. "prompt",
  199. "skill",
  200. "agent",
  201. "rules",
  202. "quality",
  203. "claude",
  204. "codex",
  205. "antigravity",
  206. "multi-tool"
  207. ],
  208. "category": "developer-tools"
  209. },
  210. {
  211. "name": "english-buddy",
  212. "source": {
  213. "source": "github",
  214. "repo": "xiaolai/english-buddy-for-claude"
  215. },
  216. "description": "English coaching with configurable on-demand and sampled modes, bounded provider calls, literal-preservation checks and progress reports; the original user prompt remains authoritative.",
  217. "version": "0.8.0",
  218. "author": {
  219. "name": "xiaolai"
  220. },
  221. "repository": "https://github.com/xiaolai/english-buddy-for-claude",
  222. "license": "ISC",
  223. "keywords": [
  224. "english",
  225. "language",
  226. "coaching",
  227. "grammar",
  228. "translation",
  229. "non-native"
  230. ],
  231. "category": "developer-tools"
  232. },
  233. {
  234. "name": "rich-terminal",
  235. "source": {
  236. "source": "github",
  237. "repo": "xiaolai/claude-rich-terminal"
  238. },
  239. "description": "Mermaid diagrams drawn inside Claude Code replies (optional Ghostty/kitty images, offline browser view), plus a truecolor status line under the prompt: git, model, context with a Token Weather forecast, cost and rate limits.",
  240. "version": "1.0.0",
  241. "author": {
  242. "name": "xiaolai"
  243. },
  244. "homepage": "https://github.com/xiaolai/claude-rich-terminal",
  245. "repository": "https://github.com/xiaolai/claude-rich-terminal",
  246. "license": "MIT",
  247. "keywords": [
  248. "mermaid",
  249. "diagrams",
  250. "terminal",
  251. "mod",
  252. "markdown",
  253. "statusline",
  254. "status-line"
  255. ],
  256. "category": "developer-tools"
  257. },
  258. {
  259. "name": "ui-tokenize",
  260. "source": {
  261. "source": "github",
  262. "repo": "xiaolai/ui-tokenize"
  263. },
  264. "description": "Block hardcoded UI values from LLM-written code — rewrite-first PreToolUse hook silently corrects literals to design-token references on the way to disk; uncertain matches deny with structured suggestions (strict mode, default) or surface as PostToolUse advisories (advisory mode); per-project surfaces allowlist narrows which file kinds the hook scans, plus an ignore glob list excludes paths (test fixtures, generated or vendored code) from hooks and audit alike; /ui-tokenize:review dispatches the token-reviewer agent to flag semantic mis-picks (right token vs. just any token); tokenize__* MCP tools for autonomous recovery",
  265. "version": "0.4.6",
  266. "author": {
  267. "name": "xiaolai"
  268. },
  269. "repository": "https://github.com/xiaolai/ui-tokenize",
  270. "license": "ISC",
  271. "keywords": [
  272. "design-tokens",
  273. "ui",
  274. "css",
  275. "tailwind",
  276. "linting",
  277. "hooks",
  278. "mcp"
  279. ],
  280. "category": "developer-tools"
  281. },
  282. {
  283. "name": "ui-responsive",
  284. "source": {
  285. "source": "github",
  286. "repo": "xiaolai/ui-responsive"
  287. },
  288. "description": "Advisory responsive-design coach — flags off-catalog breakpoints, bare 100vh, fixed widths without max-width, and stylesheets with no @media; surfaces findings as PostToolUse additionalContext, never blocks tool calls",
  289. "version": "0.1.4",
  290. "author": {
  291. "name": "xiaolai"
  292. },
  293. "repository": "https://github.com/xiaolai/ui-responsive",
  294. "license": "ISC",
  295. "keywords": [
  296. "responsive",
  297. "css",
  298. "media-queries",
  299. "viewport",
  300. "breakpoints",
  301. "advisory",
  302. "hooks",
  303. "mcp"
  304. ],
  305. "category": "developer-tools"
  306. },
  307. {
  308. "name": "north-star",
  309. "source": {
  310. "source": "github",
  311. "repo": "xiaolai/north-star-system-prompt"
  312. },
  313. "description": "A 260-token system prompt that overrides three structural presumptions every RLHF-trained LLM inherits from training: that you want confirmation, that old scarcity still applies, that best practices are ceilings.",
  314. "version": "0.1.5",
  315. "author": {
  316. "name": "xiaolai"
  317. },
  318. "repository": "https://github.com/xiaolai/north-star-system-prompt",
  319. "license": "ISC",
  320. "keywords": [
  321. "system-prompt",
  322. "stance",
  323. "judgment",
  324. "anti-sycophancy",
  325. "first-principles"
  326. ],
  327. "category": "developer-tools"
  328. },
  329. {
  330. "name": "eou-foundry",
  331. "source": {
  332. "source": "github",
  333. "repo": "xiaolai/eou-foundry"
  334. },
  335. "description": "Recursive governance for Executable Operating Units (EOUs). Faceted classification, generating-EOU constraints, ECP-governed change, no-self-approval. v0.7.0: Stage 0 (reference-grounded captured_workflow + per-app domain_values constitutional layer + Rule 96). v0.8.0: agentic judgment (judgment_authorized flag, value_invocations trace, F14–F17 taxonomy, judgment_maturity J0–J4 axis, $audit-judgment skill, Rule 97, counterfactual-swap audit).",
  336. "version": "0.8.4",
  337. "author": {
  338. "name": "xiaolai"
  339. },
  340. "repository": "https://github.com/xiaolai/eou-foundry",
  341. "license": "ISC",
  342. "keywords": [
  343. "eou",
  344. "governance",
  345. "audit",
  346. "schema",
  347. "ecp",
  348. "foundry",
  349. "executable-operating-unit",
  350. "workflow"
  351. ],
  352. "category": "governance"
  353. },
  354. {
  355. "name": "bureau",
  356. "source": {
  357. "source": "github",
  358. "repo": "xiaolai/bureau"
  359. },
  360. "description": "Turn AI sessions into a maintained, human-reviewed knowledge base: capture sessions to append-only logbooks, compile into consistency-checked cabinet dossiers gated by trust tiers (proposed → verified → canonical), and render an offline gazette (built by the bundled press). A typed review queue (bureau:review) orders the backlog upstream-first and names the exact action per page (approve / reapprove / confirm / resolve / repair); a human applies decisions one at a time or as a reviewed, content-bound, commit-gated batch (approve --from a manifest, or --all with a warning). Record architecture decisions as MADR ADR pages (bureau:adr) with typed supersedes edges — a superseded decision leaves current fact only once the superseding ADR is content-bound approved (ADR-0006). Delegate the review queue to Codex as your representative (bureau:codex-review): it recommends approve/hold, and where a workspace opts the codex authority into trust_policy it commits under --by codex — an honest machine authority, never a human one (ADR-0007). Bulk-approve the whole backlog in one confirmation (bureau:approve-all): the AI shows the batch and confirms, then hands you the single --by human line to fire yourself — it never signs for you. A deterministic recursion engine tracks claim-level dependencies (rests_on + author-anchored spans) via an append-only decision log, per-span revisions, an early-cutoff gate, and an fsck byte-fixpoint — so changing an upstream claim flags every downstream page for review. A live Engine view (bureau:serve) paints three signals onto the board as you edit — dependency freshness (needs-review/stale), artifact currency (a verified file that drifted out from under a claim), and a convergence trend (is the canon settling or thrashing) — and git-backed versioning renders any past board (build --at), diffs two versions, and pins named snapshots. Enable a crew of specialized agents or author your own. Karpathy LLM-wiki pattern + session provenance + a human review gate. Self-contained — no separate install.",
  361. "version": "1.0.6",
  362. "author": {
  363. "name": "xiaolai"
  364. },
  365. "repository": "https://github.com/xiaolai/bureau",
  366. "license": "MIT",
  367. "keywords": [
  368. "knowledge-base",
  369. "llm-wiki",
  370. "memory",
  371. "provenance",
  372. "session-capture",
  373. "review-gate",
  374. "ssot"
  375. ],
  376. "category": "developer-tools"
  377. },
  378. {
  379. "name": "xros",
  380. "source": {
  381. "source": "github",
  382. "repo": "xiaolai/xros"
  383. },
  384. "description": "XROS — an eXecutable Research Operating System. Four commands: compile a long-horizon investigation into a verifiable methodology spec; sharpen an un-checkable question (orient a newcomer in a field's vocabulary → falsifiable claim → best-available check, with its ceiling); run the Tier-A/B multi-agent engine (diverse independent routes, adversarial refutation) gated on a real oracle's exit code; or reason through a no-oracle Tier-C claim with premises, pre-mortem, and dated tripwires. Founding rule: no verification, no claim. Ships a bundled dependency-free validator and conformance suite.",
  385. "version": "0.3.4",
  386. "author": {
  387. "name": "xiaolai"
  388. },
  389. "repository": "https://github.com/xiaolai/xros",
  390. "license": "MIT",
  391. "keywords": [
  392. "research",
  393. "verification",
  394. "methodology",
  395. "multi-agent",
  396. "workflow",
  397. "falsifiability"
  398. ],
  399. "category": "developer-tools"
  400. },
  401. {
  402. "name": "mac-it-guy-pro",
  403. "source": {
  404. "source": "github",
  405. "repo": "xiaolai/mac-it-guy-pro"
  406. },
  407. "description": "Personal IT guy for non-technical macOS users — 12 plain-language commands, 4 agents, observation-first onboarding, a machine profile that retires its own stale beliefs by retesting them, a locked and transactional state writer, a PreToolUse guard that blocks destructive shell commands, a toolbox that turns repeated chores into reusable micro-tools and offers automations you did not know to ask for, learning maps built from your own measurements, and answers in your chosen language while everything on disk stays English. Ships a Codex layout with the same hooks. macOS only. 129 assertions.",
  408. "version": "1.9.6",
  409. "author": {
  410. "name": "xiaolai"
  411. },
  412. "homepage": "https://github.com/xiaolai/mac-it-guy-pro",
  413. "repository": "https://github.com/xiaolai/mac-it-guy-pro",
  414. "license": "MIT",
  415. "keywords": [
  416. "it-support",
  417. "maintenance",
  418. "cleanup",
  419. "file-organization",
  420. "backup",
  421. "automation",
  422. "non-technical-users",
  423. "macos",
  424. "privacy",
  425. "wifi",
  426. "networking",
  427. "tutoring",
  428. "learning"
  429. ],
  430. "category": "productivity"
  431. },
  432. {
  433. "name": "compute-ladder",
  434. "source": {
  435. "source": "github",
  436. "repo": "xiaolai/compute-ladder-for-claude"
  437. },
  438. "description": "Compute routing with guarded effort requests, a measured cheap-model worker and reports of observed main-agent and subagent effort; runtime escalation must be verified.",
  439. "version": "0.2.0",
  440. "author": {
  441. "name": "xiaolai"
  442. },
  443. "repository": "https://github.com/xiaolai/compute-ladder-for-claude",
  444. "license": "ISC",
  445. "keywords": [
  446. "effort",
  447. "model",
  448. "routing",
  449. "reasoning",
  450. "cost"
  451. ],
  452. "category": "developer-tools"
  453. },
  454. {
  455. "name": "dev-office",
  456. "source": {
  457. "source": "github",
  458. "repo": "xiaolai/dev-office"
  459. },
  460. "description": "A lean, self-measuring dev office for Claude Code and Codex CLI: three short agents (planner, implementer, verifier), four skills (adr, release, repo-init, tidy), perception hooks, test tiers, git routine and tidy, all host-neutral behind a single dispatcher with a four-layer config resolver (defaults, user, repo, repo-local).",
  461. "version": "0.1.1",
  462. "author": {
  463. "name": "xiaolai"
  464. },
  465. "repository": "https://github.com/xiaolai/dev-office",
  466. "license": "ISC",
  467. "keywords": [
  468. "agents",
  469. "codex",
  470. "skills",
  471. "hooks",
  472. "testing",
  473. "adr",
  474. "release",
  475. "multi-tool"
  476. ],
  477. "category": "developer-tools"
  478. }
  479. ]
  480. }
README.md · README · 164 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # claude-plugin-marketplace
  2. Central marketplace for **Claude Code** and **OpenAI Codex CLI** plugins by xiaolai.
  3. Two manifest files live in this repo:
  4. - `.claude-plugin/marketplace.json` — Claude Code entries (read by `claude plugin install`)
  5. - `.agents/plugins/marketplace.json` — Codex CLI entries (read by `codex plugin install`)
  6. Each plugin repo can ship both layouts in parallel: `.claude-plugin/` for Claude Code, `.codex-plugin/` + `codex/` tree for Codex. The two ecosystems coexist in one source repo per plugin.
  7. ## Installation
  8. For Claude Code:
  9. ```bash
  10. claude plugin marketplace add xiaolai/claude-plugin-marketplace
  11. ```
  12. For Codex CLI:
  13. ```bash
  14. codex plugin marketplace add xiaolai/claude-plugin-marketplace
  15. ```
  16. ## Available Plugins (Claude Code)
  17. | Plugin | Description | Version |
  18. |--------|-------------|---------|
  19. | [cc-suite](https://github.com/xiaolai/cc-suite) | CC Suite — one plugin to bridge and delegate across Claude Code, Codex CLI, and Antigravity: single-source AGENTS.md, shared skills, mirrored hooks and MCP servers, full Claude↔Codex bidirectional delegation (including Codex reading Claude's session history), a Claude→Grok Build delegation lane over ACP, a bounded read-only Claude→Qwen Code review lane, project-scoped advisor agents, opt-in bridging to more coding agents (Grok Build, opencode, Qwen Code, Kimi CLI), and a cross-repo sweep that repairs bridge leftovers in every bridged project at once (dead MCP registrations, and skills symlinks left pointing at a pruned plugin version). Supersedes cc-bridge and codex-toolkit. | 2.5.0 |
  20. | [tdd-guardian](https://github.com/xiaolai/tdd-guardian-for-claude) | TDD Guardian — per-lane gates (unit/integration/e2e/contract), spec-strength S1-S6, adversarial spec review, red receipts, per-path critical thresholds, 9-format coverage merging | 0.10.2 |
  21. | [echo-sleuth](https://github.com/xiaolai/echo-sleuth-for-claude) | Echo Sleuth — mine past conversations, manage memory lifecycle, extract knowledge | 0.4.4 |
  22. | [loc-guardian](https://github.com/xiaolai/loc-guardian-for-claude) | LOC Guardian — enforce per-file pure LOC limits; deterministic counting, per-file ceilings and exemptions, extraction plans measured in pure LOC, and a `--check` exit-code mode for CI and hooks | 0.4.2 |
  23. | [grill](https://github.com/xiaolai/grill-for-claude) | Deep codebase interrogation: a bounded three-finding quick review by default, with explicit full multi-agent reviews, five review styles and eight pressure tests. | 1.4.0 |
  24. | [reason-grill](https://github.com/xiaolai/reason-grill-for-claude) | Deep argument interrogation: a bounded quick review by default, with an explicit full adversarial panel and evidence-grounded verdicts. | 0.4.0 |
  25. | [docs-guardian](https://github.com/xiaolai/docs-guardian-for-claude) | Documentation freshness, accuracy and coverage checks, plus commit and push guards that resolve the target repository and map outgoing source changes to documentation. | 0.3.0 |
  26. | [nlpm](https://github.com/xiaolai/nlpm) | NLPM — score, check, fix, and test NL artifacts across **Claude Code, Codex CLI, and Antigravity**; tier-aware scoring with per-tool overlays (universal `nlpm:conventions` floor + `conventions-claude`, `conventions-codex`, `conventions-antigravity` overlays); per-tool Hooks tables (the three event vocabularies aren't 1:1 mappable); standalone Python validator (`bin/nlpm-check`) remains tool-agnostic for pre-commit hooks and CI; manifest-vs-disk consistency check still the differentiator in the Claude ecosystem | 1.4.3 |
  27. | [english-buddy](https://github.com/xiaolai/english-buddy-for-claude) | English coaching with configurable on-demand and sampled modes, bounded provider calls, literal-preservation checks and progress reports; the original user prompt remains authoritative. | 0.8.0 |
  28. | [rich-terminal](https://github.com/xiaolai/claude-rich-terminal) | Rich Terminal — Mermaid diagrams drawn inside Claude Code replies: terminal art fitted to the window, optional images in Ghostty and kitty, and an offline browser view; replaces mermaid-preview. Also a truecolor status line under the prompt with a Token Weather forecast of the context window | 1.0.0 |
  29. | [ui-tokenize](https://github.com/xiaolai/ui-tokenize) | UI Tokenize — block hardcoded UI values; rewrite-first PreToolUse hook corrects literals to design-token references on the way to disk; configurable `strict` / `advisory` strictness; per-project `surfaces` (by file kind) and `ignore` (by path) exclusion honored by hooks and audit; `/ui-tokenize:review` dispatches the `token-reviewer` agent for semantic mis-pick review | 0.4.6 |
  30. | [ui-responsive](https://github.com/xiaolai/ui-responsive) | UI Responsive — advisory responsive-design coach; flags off-catalog breakpoints, bare 100vh, fixed widths without max-width via PostToolUse additionalContext | 0.1.4 |
  31. | [north-star](https://github.com/xiaolai/north-star-system-prompt) | North Star — 260-token system prompt overriding three RLHF-inherited presumptions (independence, calibration, first-principles); ambient + slash command + subagent layered delivery | 0.1.5 |
  32. | [mac-it-guy-pro](https://github.com/xiaolai/mac-it-guy-pro) | Personal IT guy for non-technical macOS users — checkups, safe cleanup, undoable file organising, evidence-first diagnosis, backups with a restore drill, home network, private internet access, automation that leaves reusable tools behind, and a tutor grounded in your machine's own numbers; memory that retires stale beliefs by retesting them; 162 test assertions | 1.9.6 |
  33. | [eou-foundry](https://github.com/xiaolai/eou-foundry) | EOU Foundry — recursive governance for Executable Operating Units (EOUs): faceted classification, generating-EOU constraints, ECP-governed change, no-self-approval. 12 skills covering candidate generation, audit, specify, refactor, promote, foundry-wide audit, ECP authoring, init scaffolding, Stage 0 capture, and judgment audit. | 0.8.4 |
  34. | [bureau](https://github.com/xiaolai/bureau) | Bureau — turn AI sessions into a maintained, human-reviewed knowledge base: capture → compile → review → query, gated by trust tiers (proposed → verified → canonical), with a BUREAU.md instruction (imported by CLAUDE.md) that makes every session honor them; renders to an offline gazette (built by the bundled press). A typed review queue (bureau:review) orders the backlog upstream-first and names the action per page; a human applies decisions per-page or as a reviewed, content-bound, commit-gated batch (approve --from / --all). A deterministic recursion engine tracks claim-level dependencies (rests_on + author-anchored spans) so changing an upstream claim flags every downstream page for review; a live Engine view (bureau:serve) shows three signals as you edit — dependency freshness (needs-review/stale), artifact currency (a verified file that drifted out from under a claim), and a convergence trend — and git-backed versioning renders any past board, diffs two versions, and pins named snapshots. Records architecture decisions as MADR ADR pages (bureau:adr) with typed supersedes edges — superseded only once the superseding ADR is approved (ADR-0006). Delegate the review queue to Codex as your representative (bureau:codex-review) — it advises, or, where a workspace opts the codex authority in, commits under --by codex (ADR-0007). Bulk-approve the whole backlog in one confirmation (bureau:approve-all) — the AI prepares and confirms, you fire the single --by human line. Enables a crew of specialized agents. Self-contained. | 1.0.6 |
  35. | [xros](https://github.com/xiaolai/xros) | XROS — executable research operating system. Four commands: **compile** a long-horizon investigation into a verifiable methodology spec; **sharpen** an un-checkable question (orient a newcomer in a field's vocabulary → falsifiable claim → best-available check, with its ceiling); **run** the Tier-A/B multi-agent engine (diverse routes, adversarial refutation) gated on a real oracle's exit code; or **reason** through a no-oracle Tier-C claim with premises, pre-mortem, and dated tripwires. Founding rule: no verification, no claim. Ships a bundled dependency-free validator + conformance suite. | 0.3.4 |
  36. | [compute-ladder](https://github.com/xiaolai/compute-ladder-for-claude) | Compute routing with guarded effort requests, a measured cheap-model worker and reports of observed main-agent and subagent effort; runtime escalation must be verified. | 0.2.0 |
  37. ## Available Plugins (Codex CLI)
  38. Codex ports are added incrementally as each plugin is converted. Status table — entries are removed from "pending" and added here once their `.codex-plugin/` artifacts are committed and smoke-tested.
  39. Most ports keep their skills under `codex/skills/`. `xros` instead ships a **single root `skills/` tree** shared by Codex, Google Antigravity, and xAI Grok (all three implement the same `skills/<name>/SKILL.md` contract), with its `.codex-plugin/plugin.json` pointing at `./skills/`. Antigravity and Grok are installed directly from the plugin repo (`agy plugin install <git-url>` / `grok plugin install xiaolai/xros --trust`), not through this marketplace — though Grok also reads Claude Code marketplaces automatically, so `grok plugin install xros --trust` works once this marketplace is registered.
  40. | Plugin | Description | Version | Status |
  41. |--------|-------------|---------|--------|
  42. | [grill](https://github.com/xiaolai/grill-for-claude) | Deep codebase interrogation: a bounded three-finding quick review by default, with explicit full multi-agent reviews, five review styles and eight pressure tests. | 1.4.0 | Install smoke-tested with Codex CLI 0.144.3 |
  43. | [reason-grill](https://github.com/xiaolai/reason-grill-for-claude) | Deep argument interrogation: a bounded quick review by default, with an explicit full adversarial panel and evidence-grounded verdicts. | 0.4.0 | Install smoke-tested with Codex CLI 0.144.3 |
  44. | [eou-foundry](https://github.com/xiaolai/eou-foundry) | EOU Foundry — turn messy workflows into auditable Executable Operating Units with recursive governance (12 skills: candidate generation, audit, specify, refactor, promote, foundry-wide audit, ECP authoring, init scaffolding, Stage 0 capture, judgment audit). v0.7.0 ships Stage 0 (captured_workflow + per-app domain_values constitutional layer + Rule 96 consumption). v0.8.0 ships agentic judgment (judgment_authorized flag, value_invocations trace, F14–F17 taxonomy, judgment_maturity J0–J4 axis, $audit-judgment skill, Rule 97, counterfactual-swap audit). | 0.8.4 | Install smoke-tested with Codex CLI 0.144.3 |
  45. | [nlpm](https://github.com/xiaolai/nlpm) | NLPM — reference-knowledge skills (17): the 50 Rules, the 100-point scoring rubric, per-tool conventions (Claude Code / Codex CLI / Antigravity), anti-patterns, vocabulary discipline, and authoring guides. Knowledge skills, not commands — `$nlpm-rules` + `$nlpm-scoring` to score an artifact, `$nlpm-conventions-codex` for the Codex layout. The interactive `/nlpm:*` linting commands stay a Claude Code plugin (they orchestrate sub-agents); cross-tool deterministic checks use the standalone `bin/nlpm-check`. | 1.4.3 | Install smoke-tested with Codex CLI 0.159.2 (GitHub source, temporary `CODEX_HOME`): 17 skills, no `source-command-*` duplicates, no hooks; command/agent orchestration stays Claude-only |
  46. | [xros](https://github.com/xiaolai/xros) | XROS — an eXecutable Research Operating System. Four skills (`$xros-compile`, `$xros-sharpen`, `$xros-run`, `$xros-reason`): turn an investigation into a verifiable methodology spec, then gate the verdict on a real oracle's exit code. Founding rule: no verification, no claim. Ships a dependency-free validator + conformance suite. | 0.3.4 | Install smoke-tested with Codex CLI 0.144.3 |
  47. | [mac-it-guy-pro](https://github.com/xiaolai/mac-it-guy-pro) | Personal IT guy for non-technical macOS users — checkups, safe cleanup, undoable file organising, evidence-first diagnosis, backups with a restore drill, home network, automation that leaves reusable tools behind, and a tutor grounded in your machine's own numbers. PreToolUse guard and SessionStart digest both run under Codex. macOS only. | 1.9.6 | Install smoke-tested with Codex CLI 0.159.2 (GitHub source, temporary `CODEX_HOME`; 8 skills and both hooks listed); hook firing inside a live session not yet exercised |
  48. | [tdd-guardian](https://github.com/xiaolai/tdd-guardian-for-claude) | TDD Guardian — per-lane gates, spec-strength S1-S6, adversarial spec review, red receipts, critical-path thresholds, coverage merging and mutation testing as 11 workflow skills (`$tdd-guardian-workflow`, `$tdd-guardian-gate`, ...). PreToolUse commit/push freshness hook runs under Codex; Claude Code's TaskCompleted auto-gate has no Codex event, so `$tdd-guardian-gate` runs those lanes. | 0.10.2 | Install smoke-tested with Codex CLI 0.159.2 (GitHub source, temporary `CODEX_HOME`; skill listing checked); hook firing inside a live session not yet exercised |
  49. | [loc-guardian](https://github.com/xiaolai/loc-guardian-for-claude) | LOC Guardian — `$loc-guardian-scan` counts pure LOC through a tested reducer (no model arithmetic), flags files over the limit, and proposes extractions measured with tokei; `$loc-guardian-init` sets the limit and rules. | 0.4.2 | Install smoke-tested with Codex CLI 0.159.2 (GitHub source, temporary `CODEX_HOME`; skill listing checked) |
  50. | [docs-guardian](https://github.com/xiaolai/docs-guardian-for-claude) | Documentation freshness, accuracy and coverage checks, plus commit and push guards that resolve the target repository and map outgoing source changes to documentation. | 0.3.0 | Install smoke-tested with Codex CLI 0.159.2 (GitHub source, temporary `CODEX_HOME`; skill listing checked); hook firing inside a live session not yet exercised |
  51. | [english-buddy](https://github.com/xiaolai/english-buddy-for-claude) | English coaching with configurable on-demand and sampled modes, bounded provider calls, literal-preservation checks and progress reports; the original user prompt remains authoritative. | 0.7.0 | Smoke-tested with Codex CLI 0.159.2 (GitHub source, temporary `CODEX_HOME`): 17 skills listed, the hook corrected a prompt and logged it, and the report skills read that history; trust was bypassed for the run, and `systemMessage` display in the TUI is unverified |
  52. **Pending ports**: none. echo-sleuth is not ported: it mines and manages Claude Code's own transcripts and memory files, so under Codex it would be blind to Codex's sessions, and [`cc-suite`](https://github.com/xiaolai/cc-suite) already gives Codex read access to Claude history. The Claude↔Codex delegation lane is now handled by [`cc-suite`](https://github.com/xiaolai/cc-suite) (single plugin, bidirectional). `codex-guardian` (Codex-artifact auditor) remains a planned future addition for the Codex-only audit niche.
  53. ## Installing Plugins
  54. ### Global (all projects)
  55. ```bash
  56. claude plugin install cc-suite@xiaolai --scope user
  57. claude plugin install tdd-guardian@xiaolai --scope user
  58. claude plugin install echo-sleuth@xiaolai --scope user
  59. claude plugin install loc-guardian@xiaolai --scope user
  60. claude plugin install grill@xiaolai --scope user
  61. claude plugin install docs-guardian@xiaolai --scope user
  62. ```
  63. ### Codex installs
  64. **One-time setup** (shell):
  65. ```bash
  66. codex plugin marketplace add xiaolai/claude-plugin-marketplace
  67. ```
  68. Codex registers this as marketplace name `xiaolai`.
  69. **Per-plugin install** (shell):
  70. ```bash
  71. codex plugin list --marketplace xiaolai --available
  72. codex plugin add grill@xiaolai
  73. ```
  74. You can also install from inside a Codex session:
  75. 1. Start a session: `codex` (in your project directory)
  76. 2. Type `/plugins` — opens the plugin TUI
  77. 3. Find grill in the xiaolai marketplace, install/enable it
  78. **Invoking a plugin** (inside a Codex session):
  79. Codex uses the **skill** prefix `$`, not slash commands. Type:
  80. ```
  81. $grill-roast
  82. ```
  83. Or just describe the task in natural language ("do a multi-angle audit of this codebase") and Codex's auto-match will load the skill from its description.
  84. (More entries to come as Codex ports land.)
  85. ### Project only (current project)
  86. ```bash
  87. claude plugin install cc-suite@xiaolai --scope project
  88. claude plugin install tdd-guardian@xiaolai --scope project
  89. claude plugin install echo-sleuth@xiaolai --scope project
  90. claude plugin install loc-guardian@xiaolai --scope project
  91. claude plugin install grill@xiaolai --scope project
  92. claude plugin install docs-guardian@xiaolai --scope project
  93. ```
  94. ### Scope reference
  95. | Scope | Flag | Effect |
  96. |-------|------|--------|
  97. | User (global) | `--scope user` | Available in all projects (default) |
  98. | Project | `--scope project` | Shared with team via `.claude/plugins.json` |
  99. | Local | `--scope local` | Local only, not committed to git |
  100. ## Managing Plugins
  101. ```bash
  102. claude plugin list # List installed plugins
  103. claude plugin update grill@xiaolai # Update to latest version
  104. claude plugin disable grill@xiaolai # Temporarily disable
  105. claude plugin enable grill@xiaolai # Re-enable
  106. claude plugin uninstall grill@xiaolai # Remove
  107. ```
  108. ## Troubleshooting
  109. ### `plugin install` says "Plugin not found in marketplace 'xiaolai'"
  110. The marketplace is a local git clone, and `claude plugin install` does **not** auto-refresh it before resolving the plugin name. If a plugin was added to the marketplace after your local clone was last updated, install will fail with a misleading "not found" error.
  111. Refresh the marketplace, then retry:
  112. ```bash
  113. claude plugin marketplace update xiaolai
  114. claude plugin install <plugin-name>@xiaolai --scope user
  115. ```
  116. This is a Claude Code CLI limitation, not a marketplace configuration issue. The plugin is genuinely listed in `marketplace.json`; your local copy is just stale.
  117. ## Local installation health
  118. `python3 scripts/plugin-health.py /path/to/claude-plugins` inventories source versions, cached installations, scope and initialization evidence. It is read-only. Registration does not prove a plugin loaded or that its gate was exercised; those require a fresh runtime load and behavior checks.

Ratings and comments

Sign in to rate this skill.

Sign in

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