Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Capta1nRaj/goshipitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/capta1nraj/goshipit/cursor)<a href="https://agentmods.dev/rules/capta1nraj/goshipit/cursor"><img src="https://agentmods.dev/badge/rules/capta1nraj/goshipit/cursor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/capta1nraj/goshipit/cursor"><img src="https://agentmods.dev/badge/rules/capta1nraj/goshipit/cursor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00129 | $0.02077 |
| Opus 5.5 | $0.00052 | $0.00831 |
| Sonnet 5.5 | $0.00026 | $0.00415 |
| Haiku 4.5 | $0.00013 | $0.00208 |
Grade A, and why
cursor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
goshipit — Pre-launch Codebase Audit
210 checks. Stack-aware. Severity-weighted score out of 100. Saves prelaunch-report.md.
References path: ~/.goshipit/references/
Step 1 — Stack Detection
Run these terminal commands to detect the stack:
ls -la
cat package.json 2>/dev/null
cat pyproject.toml 2>/dev/null
cat go.mod 2>/dev/null
cat Cargo.toml 2>/dev/null
ls *.config.* *.toml *.yaml *.yml Makefile Dockerfile* 2>/dev/null
Infer: framework, language, runtime, DB, auth lib, build tool, deploy target.
turbo.json/nx.json→ monorepobun.lockb→ Bun runtimepnpm-workspace.yaml→ pnpm monorepofly.toml/vercel.json/netlify.toml/render.yaml→ deploy targetecosystem.config.*→ PM2nginx.conf→ Nginx
Guard: No project files found → tell user "No codebase detected. Run goshipit from project root." and stop.
Report detected stack before asking questions.
Step 2 — Category Selection
Ask the user (in chat):
Which areas to audit? (reply with numbers, comma-separated, or "all")
1. All areas — full audit (recommended) — 210 checks A-O: A Secrets 9 · C Security 35 · B Quality 18 · D Tests 4 · E Build 15 · F Reliability 21 · G Hygiene 14 · I Deploy 15 · J SEO 14 · K PWA 5 · L Ecom 13 · M Billing 9 · N Legal 7 · O Agent 22 (+ H A11y 9 via Next)
2. Secrets & Environment — .env in git, hardcoded keys, multi-env drift, webhook URLs, test-mode keys — A (9)
3. Security — SQLi, XSS, CORS, CSP/HSTS, rate-limit, CSRF, CVEs, BOLA/IDOR, auth, SSRF — C (35)
4. Code Quality — console.log, TODOs, dead code, complexity, leaks, promises, strict TS — B (18)
5. Tests — suite pass, coverage, skipped, E2E — D (4)
6. Build & Performance — build errors, types, bundle, N+1, images, cache, SSR — E (15)
7. Reliability — runtime pin, error handling, monitoring, DB migrations, pooling — F (21)
8. Hygiene — conflicts, .gitignore, README, large files, linter, CI secrets — G (14)
9. Deploy & Infra — Docker non-root, Vercel/Render, Nginx, PM2, K8s limits/probes — I (15)
10. SEO, PWA, Ecom, Billing, Legal & Agent — SEO meta, PWA SW, tracking, billing webhooks, GDPR, llms.txt, MCP/A2A, x402 — J,K,L,M,N,O (77 combined)
Include accessibility checks? (yes/no)
Fix mode? (audit-only / audit+autofix)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 197 lines · 129 tokens per session scan A 7cecc79e7e5d
cursor is a cursor rule published in the GitHub repository Capta1nRaj/goshipit (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 129 tokens to every session and 2,077 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
ai-gateway-smoke-mandatory
AI Gateway / trafficevent changes require an ai-gateway smoke run before "done".
verificate-gate
Verificate merge gate — every substantive AI-written change must pass validateaioutput before being presented as complete.
python-code-validator
Validate generated Python at every step, not once at the end.
jest
Jest: describe/it, matchers, mocking, async testing.
playwright
Playwright: e2e testing, page objects, fixtures, assertions.
vitest
Vitest: unit testing, mocking, coverage, snapshot testing.