Skip to content
Back to search

ultraship

"ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness check, penetration testing, code review, competitive analysis, incident response. 1 dependency. 180 tests. MIT.

Safety scan

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

Checked today

Check it deeper on your machine

Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/Houseofmvps/ultraship with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/Houseofmvps/ultraship'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/houseofmvps--ultraship/badge.svg)](/listings/houseofmvps--ultraship)

HTML

<a href="/listings/houseofmvps--ultraship"><img src="/api/listings/houseofmvps--ultraship/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.

# Claude Code plugin
claude plugin marketplace add Houseofmvps/ultraship
claude plugin install ultraship

# Or standalone via npx
npx ultraship ship .
npx ultraship seo .
npx ultraship security .

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 · 58 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": "ultraship",
  3. "owner": {
  4. "name": "Houseofmvps",
  5. "email": "houseofmvps2024@gmail.com"
  6. },
  7. "metadata": {
  8. "description": "Claude Code plugin — 41 tools, 45 skills, 13 agents, 16 commands. Currency Guard keeps Claude on current docs, not stale training data. Elite SEO strategy with AI traffic tracking, IndexNow, GSC-GA4 cross-reference, CTR anomalies, brand filtering, keyword intelligence, index doctor, codebase index, pentest, ship, launch, grow, rescue."
  9. },
  10. "plugins": [
  11. {
  12. "name": "ultraship",
  13. "description": "Full lifecycle plugin: plan, build, test, review, ship, deploy, verify, reflect. Currency Guard keeps Claude on current docs. 41 tools, 45 skills, 13 agents.",
  14. "version": "2.13.2",
  15. "source": "./",
  16. "author": {
  17. "name": "Houseofmvps",
  18. "email": "houseofmvps2024@gmail.com"
  19. },
  20. "homepage": "https://github.com/Houseofmvps/ultraship",
  21. "repository": "https://github.com/Houseofmvps/ultraship",
  22. "license": "MIT",
  23. "keywords": [
  24. "ship",
  25. "seo",
  26. "geo",
  27. "aeo",
  28. "security",
  29. "code-review",
  30. "lighthouse",
  31. "performance",
  32. "workflow",
  33. "tdd",
  34. "deploy",
  35. "indie-hacker",
  36. "saas",
  37. "developer-tools",
  38. "browser-testing",
  39. "competitive-analysis",
  40. "launch",
  41. "incident-response",
  42. "growth",
  43. "cost-tracking",
  44. "onboarding",
  45. "architecture",
  46. "pentest",
  47. "penetration-testing",
  48. "vulnerability-scanner",
  49. "sprint",
  50. "canary",
  51. "retrospective",
  52. "guard",
  53. "safety",
  54. "learnings"
  55. ]
  56. }
  57. ]
  58. }
README.md · README · 478 lines

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

  1. <div align="center">
  2. <img src="assets/hero-banner.jpg" alt="Ultraship — Claude Code Plugin" width="100%"/>
  3. ### Claude Code plugin. 43 expert-level skills for building, shipping, and scaling production software. 37 audit tools (accessibility, vibe-coding security, AI evals, pentest, code quality, bundle size, SEO + AI Readiness check) plus a blocking ship-gate close the loop before deploy. A built-in Currency Guard keeps Claude on current docs, not stale training data.
  4. [![npm version](https://img.shields.io/npm/v/ultraship?style=for-the-badge&logo=npm&color=CB3837)](https://www.npmjs.com/package/ultraship)
  5. [![npm downloads](https://img.shields.io/npm/dm/ultraship?style=for-the-badge&logo=npm&color=blue&label=Monthly%20Downloads)](https://www.npmjs.com/package/ultraship)
  6. [![npm total](https://img.shields.io/npm/dt/ultraship?style=for-the-badge&logo=npm&color=cyan&label=Total%20Downloads)](https://www.npmjs.com/package/ultraship)
  7. [![GitHub stars](https://img.shields.io/github/stars/Houseofmvps/ultraship?style=for-the-badge&logo=github&color=gold)](https://github.com/Houseofmvps/ultraship/stargazers)
  8. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow?style=for-the-badge&logo=opensourceinitiative)](LICENSE)
  9. [![CI](https://img.shields.io/github/actions/workflow/status/Houseofmvps/ultraship/ci.yml?style=for-the-badge&logo=github&label=Tests)](https://github.com/Houseofmvps/ultraship/actions)
  10. [![Sponsor](https://img.shields.io/badge/Sponsor-EA4AAA?style=for-the-badge&logo=githubsponsors&logoColor=white)](https://github.com/sponsors/Houseofmvps)
  11. ---
  12. [![Follow @kaileskkhumar](https://img.shields.io/badge/Follow%20%40kaileskkhumar-000000?style=for-the-badge&logo=x&logoColor=white)](https://x.com/kaileskkhumar)
  13. [![LinkedIn](https://img.shields.io/badge/LinkedIn-Connect-0A66C2?style=for-the-badge&logo=linkedin)](https://www.linkedin.com/in/kailesk-khumar-soundararajan)
  14. [![houseofmvps.com](https://img.shields.io/badge/houseofmvps.com-Website-green?style=for-the-badge&logo=google-chrome&logoColor=white)](https://houseofmvps.com)
  15. [![kailxlabs.co](https://img.shields.io/badge/kailxlabs.co-Website-6366F1?style=for-the-badge&logo=google-chrome&logoColor=white)](https://www.kailxlabs.co)
  16. **Built by [Kaileskkhumar](https://www.linkedin.com/in/kailesk-khumar-soundararajan), founder of [HouseofMVPs](https://houseofmvps.com) and [Kailxlabs](https://www.kailxlabs.co)**
  17. </div>
  18. ---
  19. ```
  20. 0 dependencies · 274 tests · Node.js ESM · MIT
  21. ```
  22. ## Install
  23. ```bash
  24. # Claude Code plugin
  25. claude plugin marketplace add Houseofmvps/ultraship
  26. claude plugin install ultraship
  27. # Or standalone via npx
  28. npx ultraship ship .
  29. npx ultraship seo .
  30. npx ultraship security .
  31. ```
  32. ## How It Works
  33. ```mermaid
  34. flowchart LR
  35. U["You type a<br/>slash command"] --> S["Skill<br/>(markdown instructions)"]
  36. S --> A["Agent<br/>(dispatched worker)"]
  37. S --> T["Tools<br/>(Node.js scripts)"]
  38. A --> T
  39. T --> O["JSON Results"]
  40. O --> R["Scorecard / Report /<br/>Actionable Fixes"]
  41. style U fill:#f59e0b,stroke:#d97706,color:#000
  42. style S fill:#8b5cf6,stroke:#7c3aed,color:#fff
  43. style A fill:#3b82f6,stroke:#2563eb,color:#fff
  44. style T fill:#10b981,stroke:#059669,color:#000
  45. style R fill:#ef4444,stroke:#dc2626,color:#fff
  46. ```
  47. ```mermaid
  48. flowchart TD
  49. subgraph Lifecycle["Full Lifecycle Coverage"]
  50. direction LR
  51. I["Idea<br/>/brainstorm"] --> B["Build<br/>/sprint"]
  52. B --> AU["Audit<br/>/ship /seo /secure"]
  53. AU --> D["Ship<br/>/deploy"]
  54. D --> L["Launch<br/>/launch /compete"]
  55. L --> G["Grow<br/>/grow /cost"]
  56. G --> RE["Rescue<br/>/rescue /canary"]
  57. end
  58. style I fill:#8b5cf6,stroke:#7c3aed,color:#fff
  59. style B fill:#3b82f6,stroke:#2563eb,color:#fff
  60. style AU fill:#f59e0b,stroke:#d97706,color:#000
  61. style D fill:#10b981,stroke:#059669,color:#000
  62. style L fill:#06b6d4,stroke:#0891b2,color:#000
  63. style G fill:#84cc16,stroke:#65a30d,color:#000
  64. style RE fill:#ef4444,stroke:#dc2626,color:#fff
  65. ```
  66. ## What `/ship` Does
  67. `/ship` runs 6 tools in parallel and outputs a scorecard:
  68. ```mermaid
  69. flowchart LR
  70. SHIP["/ship"] --> SEO["seo-scanner<br/>63 rules"]
  71. SHIP --> A11Y["a11y-scanner<br/>WCAG 2.2"]
  72. SHIP --> SEC["secret-scanner<br/>+ npm audit"]
  73. SHIP --> CODE["code-profiler<br/>N+1, leaks, ReDoS"]
  74. SHIP --> BUNDLE["bundle-tracker<br/>JS/CSS/images"]
  75. SHIP --> ENV["env-validator<br/>+ migration-checker"]
  76. SEO --> SC["Scorecard<br/>READY TO SHIP"]
  77. A11Y --> SC
  78. SEC --> SC
  79. CODE --> SC
  80. BUNDLE --> SC
  81. ENV --> SC
  82. style SHIP fill:#f59e0b,stroke:#d97706,color:#000
  83. style SC fill:#10b981,stroke:#059669,color:#000
  84. style SEO fill:#3b82f6,stroke:#2563eb,color:#fff
  85. style SEC fill:#3b82f6,stroke:#2563eb,color:#fff
  86. style CODE fill:#3b82f6,stroke:#2563eb,color:#fff
  87. style BUNDLE fill:#3b82f6,stroke:#2563eb,color:#fff
  88. style ENV fill:#3b82f6,stroke:#2563eb,color:#fff
  89. ```
  90. ```
  91. +===========================================+
  92. | U L T R A S H I P S C O R E |
  93. +===========================================+
  94. | SEO + AI Vis. 92/100 ############- |
  95. | Security 95/100 ############- |
  96. | Code Quality 88/100 ###########-- |
  97. | Bundle Size 97/100 ############- |
  98. +===========================================+
  99. | OVERALL 90/100 |
  100. | STATUS READY TO SHIP |
  101. +===========================================+
  102. ```
  103. <details>
  104. <summary>Demo</summary>
  105. <img src="assets/demo.gif" alt="Ultraship — SEO audit, secret scanning, scorecard" width="100%"/>
  106. </details>
  107. ## Tools (40)
  108. Each tool is a standalone Node.js script (`node tools/<name>.mjs`). JSON output. Exit 0 always. No build step.
  109. ### Auditing
  110. | Tool | What it checks |
  111. |---|---|
  112. | `seo-scanner` | 63 rules: 39 SEO (meta tags, canonicals, headings, OG tags, structured data, sitemap, cross-page duplicate/orphan detection), 20 GEO (AI bot access in robots.txt, snippet restrictions, llms.txt, structured data for AI extraction), 4 AEO (FAQPage/HowTo/speakable schema) |
  113. | `a11y-scanner` | WCAG 2.2 A/AA static checks: missing alt text, unlabeled form controls, icon-only buttons, missing `lang`/`title`/`main`, heading order, positive tabindex, zoom disabled, duplicate ids, broken aria references. Zero false positives. |
  114. | `ship-gate` | Blocking quality gate — scores all auditors (shared math with `/ship`), compares to `.ultraship/ship-gate.json` thresholds, hard-fails on leaked secrets / critical findings, **exits 1 on fail**. Generates a pre-push hook + GitHub Actions workflow. |
  115. | `secret-scanner` | AWS keys, Stripe keys, JWT secrets, database URLs, private keys. Redacts values in output. |
  116. | `vibe-security-scanner` | Vibe-Coding Security Sentinel — context secret-scanner misses: server-only secrets behind a `NEXT_PUBLIC_`/`VITE_` prefix, a decoded Supabase `service_role` key exposed to the client, service_role in a `"use client"` file, Supabase tables with no RLS. Zero false positives. |
  117. | `eval-scanner` | Locates every LLM call site (Anthropic, OpenAI, Gemini, Mistral, Cohere, Ollama, Vercel AI SDK, LangChain) by provider + model id, detects the test runner and whether an eval suite exists. Flags AI features shipping with no evals. Seeds `/evals`. Zero false positives. |
  118. | `code-profiler` | N+1 queries, sync I/O in handlers, unbounded queries, missing indexes, memory leaks, sequential awaits, ReDoS risk |
  119. | `bundle-tracker` | JS/CSS/image sizes in build output. Detects heavy deps (`moment`→`dayjs`, `lodash`→native). History for before/after. Monorepo-aware. |
  120. | `dep-doctor` | Unused dependencies via import graph analysis (not just grep). Dead wrapper files. Outdated packages. |
  121. | `content-scorer` | Flesch-Kincaid readability, keyword density, thin content detection, GEO heading analysis |
  122. | `lighthouse-runner` | Lighthouse via headless Chrome. Core Web Vitals, render-blocking resources, diagnostics. |
  123. ### Validation
  124. | Tool | What it checks |
  125. |---|---|
  126. | `health-check` | HTTP status, response time, SSL certificate (issuer, expiry), 6 security headers |
  127. | `env-validator` | Compares `.env.example` against actual `.env`. Catches missing/empty/placeholder vars. |
  128. | `migration-checker` | Pending DB migrations for Drizzle, Prisma, Knex |
  129. | `og-validator` | Open Graph tags, image reachability, size validation |
  130. | `redirect-checker` | Redirect chains, loops, mixed HTTP/HTTPS. Sitemap-based bulk check. |
  131. | `api-smoke-test` | Hit API endpoints, check status codes, response times, CORS headers |
  132. ### Generators
  133. | Tool | What it creates |
  134. |---|---|
  135. | `sitemap-generator` | `sitemap.xml` from HTML files and routes |
  136. | `robots-generator` | AI-friendly `robots.txt` (allows GPTBot, PerplexityBot, ClaudeBot) |
  137. | `llms-txt-generator` | `llms.txt` for AI assistant discoverability |
  138. | `structured-data-generator` | JSON-LD schema markup |
  139. ### Competitive & Launch
  140. | Tool | What it does |
  141. |---|---|
  142. | `compete-analyzer` | Compares two URLs: tech stack, SEO score, security headers, response time. ASCII comparison card. |
  143. | `launch-prep` | Reads project, generates PH/Twitter/LinkedIn/HN copy, 14-item checklist, press kit |
  144. | `demo-prep` | Finds console.logs, TODOs, placeholder text, missing favicons. Scores demo readiness. |
  145. ### Operations
  146. | Tool | What it does |
  147. |---|---|
  148. | `incident-commander` | Health check + git culprit analysis + error patterns + rollback commands + post-mortem template |
  149. | `growth-tracker` | Uptime, git velocity, SEO trajectory, dep health. Stores snapshots for week-over-week comparison. |
  150. | `cost-tracker` | Log AI token usage per feature/model. Built-in pricing for Claude, GPT-4o, Gemini. Daily trends. |
  151. | `pentest-scanner` | Automated penetration testing: XSS, SQLi, SSTI, command injection, path traversal, CORS, JWT, GraphQL introspection, prototype pollution, race conditions, request smuggling. Zero false positives, every finding has proof-of-concept. |
  152. | `canary-monitor` | Post-deploy canary monitoring: HTTP status, response time, error patterns, baseline regression detection. Auto-saves baselines for future comparison. |
  153. | `retro-analyzer` | Sprint retrospective: git velocity, commit patterns (features vs fixes), test health, hot files, shipping cadence. Generates insights and recommendations. |
  154. | `learnings-manager` | Project learnings CRUD: save, search, list, prune, export. Structured knowledge that compounds across sessions. |
  155. ### Project Analysis
  156. | Tool | What it does |
  157. |---|---|
  158. | `onboard-generator` | Auto-generates developer guide: stack, directory tree, routes, schema, env vars, Mermaid diagram |
  159. | `architecture-mapper` | 4 Mermaid diagrams: system overview, route tree, DB ER, data flow. Circular dependency + orphan detection. |
  160. | `pattern-analyzer` | Analyzes testing, error handling, TypeScript usage, CI/CD, git practices. Cross-repo comparison. |
  161. | `audit-history` | Saves/compares audit scores over time |
  162. ### Integrations (optional)
  163. | Tool | What it does |
  164. |---|---|
  165. | `gsc-client` | Google Search Console: submit sitemaps, inspect URLs, query rankings (requires `ULTRASHIP_GSC_CREDENTIALS`) |
  166. | `bing-webmaster` | Bing Webmaster: submit sitemaps/URLs, IndexNow instant push, keyword research, backlinks, site-scan, URL inspection (requires `ULTRASHIP_BING_KEY`). Powers ChatGPT Search + Microsoft Copilot. |
  167. | `ga4-client` | Google Analytics 4: overview, top-pages, landing-pages, traffic-sources, conversions, user-journey, devices, realtime, **ai-traffic** (ChatGPT/Perplexity/Copilot tracking), **organic** (search-only). `--organic` flag. |
  168. | `keyword-intelligence` | 12-command keyword engine: analyze, quick-wins, cannibalization, content-gaps, intent-map, trending, high-intent, page-keywords, content-decay, difficulty, **anomalies** (CTR anomalies), **cross-reference** (GSC↔GA4). `--brand` flag for non-brand filtering. |
  169. | `index-doctor` | Index diagnosis: inspect URLs via GSC URL Inspection API, diagnose 15+ coverage states, auto-fix and submit to Bing. |
  170. ## Commands (16)
  171. > **Every skill is also a slash command.** Claude Code merged commands into skills, so `/a11y`, `/sprint`, `/pentest`, `/compete`, `/canary`, `/launch`, `/rescue`, `/grow`, `/deploy`, `/learn`, `/guard`, `/retro`, `/investigate`, `/cost`, `/onboard`, `/architecture`, `/clone-patterns`, `/demo`, `/visual-diff`, `/release`, `/seo-strategy` and `/index-fix` all work too — they live in [Skills](#skills-41) above. The commands below are the remaining dedicated command files.
  172. | Command | Description |
  173. |---|---|
  174. | `/ship` | Pre-deploy scorecard. Runs 6 auditors, scores 5 categories |
  175. | `/seo` | SEO audit (63 rules) + AI visibility checks (bot access, snippet restrictions, schema) |
  176. | `/secure` | Secret scanning + OWASP patterns + `npm audit` |
  177. | `/perf` | Lighthouse + bundle size |
  178. | `/review` | Code review with confidence-scored findings |
  179. | `/health` | Production health check |
  180. | `/codex` | Generate a compact codebase index (routes, schema, components, lib) to save AI tokens |
  181. | `/content` | Readability + keyword density analysis |
  182. | `/bundle` | Bundle size tracking |
  183. | `/profile` | Static analysis for backend anti-patterns |
  184. | `/deps` | Unused/outdated dependency detection |
  185. | `/redirects` | Redirect chain/loop detection |
  186. | `/revise-claude-md` | Update CLAUDE.md with session learnings |
  187. | `/brainstorm` | Deprecated alias → use the `brainstorming` skill |
  188. | `/write-plan` | Deprecated alias → use the `writing-plans` skill |
  189. | `/execute-plan` | Deprecated alias → use the `executing-plans` skill |
  190. ## Skills (43)
  191. Skills are markdown instruction files that shape Claude's behavior during your session. They activate based on context. When you're debugging, Claude uses the debugging skill. When you're building UI, it uses the frontend design skill.
  192. **Workflow (19):** brainstorming, planning, TDD, implementation, code review, debugging, refactoring, frontend design, API design, data modeling, git workflow, deploy pipeline, release, CLAUDE.md management, verification, browser testing, **sprint pipeline**, **investigation**, **learnings management**
  193. **Specialist (12):** SEO + AI visibility audit, **accessibility audit + auto-fix**, **deterministic ship-gate**, **AI eval harness**, security audit, **penetration testing**, performance audit, content quality, code profiling, parallel agent dispatching, **safety guardrails**, **staying current**
  194. **Growth & Intelligence (12):** competitive analysis, launch prep, incident response, growth tracking, cost tracking, onboarding, architecture mapping, pattern analysis, demo readiness, visual regression, **canary monitoring**, **sprint retrospective**
  195. ## Agents (13)
  196. Agents are dispatched by skills to run audits in parallel:
  197. `code-reviewer` · `seo-auditor` · `seo-strategist` · `security-auditor` · `pentest-auditor` · `perf-auditor` · `a11y-auditor` · `browser-verifier` · `compete-analyzer` · `launch-auditor` · `incident-responder` · `growth-tracker` · `canary-monitor`
  198. ## MCP Servers (2)
  199. | Server | Purpose |
  200. |---|---|
  201. | [Context7](https://github.com/upstash/context7) | Live library documentation. Fetches current docs for any framework/library. |
  202. | [Playwright](https://github.com/anthropics/anthropic-quickstarts/tree/main/mcp-server-playwright) | Browser automation. Navigate, screenshot, fill forms, test deployed pages. |
  203. Both lazy-start on first use. No background processes.
  204. ### Optional MCP integrations (detect-if-present)
  205. Ultraship doesn't bundle these (they need your credentials and would slow every install), but several skills use them automatically *if you've connected them*:
  206. | Connect | Sharpens |
  207. |---|---|
  208. | **Sentry** | `/rescue` pulls live production errors and maps stack traces to code instead of guessing the culprit. `/canary` confirms a post-deploy error spike before recommending rollback. |
  209. | **Vercel** | `/deploy` reads real deployment status, build logs, and which commit is live (not just a single HTTP probe). |
  210. | **Supabase** | `/deploy` verifies migration state against the actual database to catch dashboard-vs-repo drift. |
  211. Add them with `claude mcp add` (or the `/plugin` browser). When connected, the skills detect the tools and use them; when not, they fall back to the built-in static checks.
  212. ## Sprint Workflow
  213. Ultraship skills chain into a structured sprint pipeline. Each phase produces artifacts that feed the next.
  214. ```mermaid
  215. flowchart LR
  216. P["/write-plan<br/>Plan"] --> B["/execute-plan<br/>Build"]
  217. B --> T["TDD<br/>Test"]
  218. T --> R["/review + /secure<br/>Review"]
  219. R --> S["/ship + /deploy<br/>Ship"]
  220. S --> V["/canary<br/>Verify"]
  221. V --> RE["/retro + /learn<br/>Reflect"]
  222. style P fill:#8b5cf6,stroke:#7c3aed,color:#fff
  223. style B fill:#3b82f6,stroke:#2563eb,color:#fff
  224. style T fill:#06b6d4,stroke:#0891b2,color:#000
  225. style R fill:#f59e0b,stroke:#d97706,color:#000
  226. style S fill:#10b981,stroke:#059669,color:#000
  227. style V fill:#84cc16,stroke:#65a30d,color:#000
  228. style RE fill:#ec4899,stroke:#db2777,color:#fff
  229. ```
  230. | Phase | Skill | Output |
  231. |---|---|---|
  232. | Plan | `/write-plan` | Implementation plan with file map and test strategy |
  233. | Build | `/execute-plan` | Working code on a feature branch |
  234. | Test | TDD skill | Passing test suite |
  235. | Review | `/review` + `/secure` | Review report, security scan |
  236. | Ship | `/ship` + `/deploy` | Scorecard + production deploy |
  237. | Verify | `/canary` | Post-deploy health verification |
  238. | Reflect | `/retro` + `/learn` | Retrospective + saved learnings |
  239. Run `/sprint` to follow the full pipeline, or run individual phases as needed.
  240. ## Safety Guardrails
  241. `/guard` activates PreToolUse hooks that block destructive commands before they execute:
  242. ```mermaid
  243. flowchart LR
  244. CMD["Claude runs<br/>a command"] --> HOOK["PreToolUse<br/>Hook"]
  245. HOOK --> CHECK{"Destructive?"}
  246. CHECK -->|"rm -rf, DROP TABLE,<br/>git push --force,<br/>kubectl delete..."| BLOCK["BLOCKED"]
  247. CHECK -->|Safe| ALLOW["Allowed"]
  248. style HOOK fill:#f59e0b,stroke:#d97706,color:#000
  249. style BLOCK fill:#ef4444,stroke:#dc2626,color:#fff
  250. style ALLOW fill:#10b981,stroke:#059669,color:#000
  251. ```
  252. - `rm -rf`, `DROP TABLE`, `TRUNCATE` (data destruction)
  253. - `git push --force`, `git reset --hard` (git history destruction)
  254. - `git clean -f`, `git checkout .` (working directory destruction)
  255. - `kubectl delete`, `docker system prune` (infrastructure destruction)
  256. Optional directory freeze restricts all file edits to a specific path. Explicitly confirmed actions always proceed.
  257. ## Persistent Memory
  258. Ultraship enforces a **memory-first rule** at session start. The SessionStart hook detects if you have a `MEMORY.md` file and instructs Claude to read it before performing any task. Context persists across sessions. No more repeating yourself about project state, deploy status, or decisions already made.
  259. - If `MEMORY.md` is found: Claude reads memory files before doing anything
  260. - If not found: Claude suggests setting up auto-memory for persistent context
  261. No configuration needed. Just install the plugin.
  262. ## SEO + AI Visibility
  263. ```mermaid
  264. flowchart TD
  265. subgraph Data["Data Sources (optional API keys)"]
  266. GSC["Google Search Console<br/>Index status, rankings"]
  267. GA4["Google Analytics 4<br/>Traffic, AI referrals"]
  268. BING["Bing Webmaster<br/>Crawl, IndexNow, backlinks"]
  269. end
  270. subgraph Analysis["Intelligence Layer"]
  271. KW["keyword-intelligence<br/>12 commands"]
  272. IDX["index-doctor<br/>Diagnose + fix"]
  273. SCAN["seo-scanner<br/>63 rules"]
  274. end
  275. subgraph Output["Outputs"]
  276. STR["/seo-strategy<br/>90-day ranking plan"]
  277. FIX["/index-fix<br/>Auto-submit fixes"]
  278. SCORE["/seo<br/>SEO + GEO + AEO score"]
  279. end
  280. GSC --> KW
  281. GSC --> IDX
  282. GA4 --> KW
  283. BING --> IDX
  284. SCAN --> SCORE
  285. KW --> STR
  286. IDX --> FIX
  287. style GSC fill:#4285f4,stroke:#3367d6,color:#fff
  288. style GA4 fill:#e37400,stroke:#c56200,color:#fff
  289. style BING fill:#00809d,stroke:#006680,color:#fff
  290. style KW fill:#8b5cf6,stroke:#7c3aed,color:#fff
  291. style IDX fill:#8b5cf6,stroke:#7c3aed,color:#fff
  292. style SCAN fill:#8b5cf6,stroke:#7c3aed,color:#fff
  293. style STR fill:#10b981,stroke:#059669,color:#000
  294. style FIX fill:#10b981,stroke:#059669,color:#000
  295. style SCORE fill:#10b981,stroke:#059669,color:#000
  296. ```
  297. The SEO scanner checks 63 rules across three layers:
  298. - **SEO (39 rules)**: meta tags, canonicals, heading hierarchy, alt text, OG tags, sitemap, robots.txt, structured data, analytics detection, cross-page duplicate titles/descriptions, orphan page detection, canonical conflicts, thin content, internal linking
  299. - **GEO (20 rules)**: AI search visibility signals. Does `robots.txt` block GPTBot/PerplexityBot/ClaudeBot? Do `nosnippet`/`max-snippet` directives restrict AI citation eligibility? Is there `llms.txt` for AI discovery? Does structured data exist for AI extraction? These are verifiable technical signals, not ranking factor guesses.
  300. - **AEO (4 rules)**: answer engine schema checks. FAQPage, HowTo, speakable, Article/BlogPosting. These are the structured data types that enable featured snippets and voice results. We check presence, not SERP performance.
  301. Beyond the scanner, Ultraship connects to real APIs: GSC URL Inspection (actual index status), GA4 (actual AI referral traffic from ChatGPT/Perplexity/Copilot), Bing Webmaster (crawl status, IndexNow). Data-driven analysis, not estimates.
  302. ## Dogfooding
  303. `/ship` results on [SaveMRR](https://savemrr.co) (Hono + React + Drizzle pnpm monorepo, 5 packages, 41 routes):
  304. | | Backend + Dashboard | Landing (29 pages) |
  305. |---|---|---|
  306. | SEO + AI Visibility | 63 | 52 |
  307. | Security | 100 | 100 |
  308. | Code Quality | 70 | 67 |
  309. | Bundle Size | 100 | 92 |
  310. | **Overall** | **83** | **78** |
  311. 227 findings: 1 N+1 query, 33 unused deps (dead shadcn/ui wrappers via import graph), 153 SEO issues, 1 memory leak, 1 heavy dep.
  312. ## Security
  313. All tools use `execFileSync` with array args (no shell interpolation). HTTP tools import `tools/lib/security.mjs` for SSRF protection (blocks private IPs, cloud metadata, non-HTTP schemes). 10MB file read cap. 5MB response cap. Secret values redacted in output. Zero telemetry.
  314. See [SECURITY.md](SECURITY.md).
  315. ## Architecture
  316. ```mermaid
  317. flowchart TD
  318. subgraph Plugin["ultraship plugin"]
  319. MANIFEST[".claude-plugin/<br/>plugin.json"]
  320. HOOKS["hooks/<br/>SessionStart + Currency Guard + Guard"]
  321. subgraph Core["Core Loop"]
  322. SKILLS["skills/<br/>45 markdown files"]
  323. AGENTS["agents/<br/>13 agent definitions"]
  324. COMMANDS["commands/<br/>16 command files"]
  325. end
  326. subgraph Runtime["Runtime"]
  327. TOOLS["tools/<br/>41 Node.js ESM scripts"]
  328. LIB["tools/lib/<br/>security.mjs, monorepo.mjs"]
  329. end
  330. end
  331. subgraph External["External (optional)"]
  332. MCP1["Context7 MCP<br/>Live docs"]
  333. MCP2["Playwright MCP<br/>Browser automation"]
  334. GSC2["GSC / GA4 / Bing<br/>APIs"]
  335. end
  336. COMMANDS --> SKILLS
  337. SKILLS --> AGENTS
  338. SKILLS --> TOOLS
  339. AGENTS --> TOOLS
  340. TOOLS --> LIB
  341. TOOLS --> GSC2
  342. SKILLS --> MCP1
  343. SKILLS --> MCP2
  344. style MANIFEST fill:#6b7280,stroke:#4b5563,color:#fff
  345. style HOOKS fill:#f59e0b,stroke:#d97706,color:#000
  346. style SKILLS fill:#8b5cf6,stroke:#7c3aed,color:#fff
  347. style AGENTS fill:#3b82f6,stroke:#2563eb,color:#fff
  348. style COMMANDS fill:#06b6d4,stroke:#0891b2,color:#000
  349. style TOOLS fill:#10b981,stroke:#059669,color:#000
  350. style LIB fill:#059669,stroke:#047857,color:#fff
  351. style MCP1 fill:#6b7280,stroke:#4b5563,color:#fff
  352. style MCP2 fill:#6b7280,stroke:#4b5563,color:#fff
  353. style GSC2 fill:#6b7280,stroke:#4b5563,color:#fff
  354. ```
  355. - Node.js ESM (`type: module`)
  356. - 1 dependency: `htmlparser2` (SAX HTML parser, ~30KB)
  357. - Tools output JSON to stdout, exit 0 on success and failure (errors in JSON)
  358. - Skills reference tools via `${CLAUDE_PLUGIN_ROOT}/tools/<name>.mjs`
  359. - No build step. No native bindings. No `node-gyp`.
  360. ## Contributing
  361. ```bash
  362. git clone https://github.com/Houseofmvps/ultraship.git
  363. cd ultraship
  364. npm test # 180 tests, node:test
  365. node tools/<tool>.mjs # Run any tool directly
  366. ```
  367. [Open an issue](https://github.com/Houseofmvps/ultraship/issues) or submit a PR.
  368. ## License
  369. MIT
  370. ---
  371. Built by [Kailesk Khumar](https://www.linkedin.com/in/kailesk-khumar), founder of [HouseofMVPs](https://houseofmvps.com) · [Book a 30-min strategy call](https://cal.com/houseofmvps/30-min-strategy-call-with-our-founder)

Ratings and comments

Sign in to rate this skill.

Sign in

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