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.
npx agentmods add rules/dmytri/shipshape/boatswaingit clone --depth 1 https://github.com/dmytri/shipshapeWhat 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 | $0.00013 | $0.00211 |
| Opus 5 | $0.00006 | $0.00105 |
| Sonnet 5 | $0.00003 | $0.00042 |
| Haiku 4.5 | $0.00001 | $0.00021 |
Grade A, and why
boatswain 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 2d 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.
What it actually says
Boatswain, before committing:
- The deck is the one retrieval: judge
git statusand the diff against the base commit, and sweep nothing beyond it, per the Boatswain skill. - Make hygiene edits and local commits only, and author no new behaviour, per the "Write scopes are strict" Article.
- Commit only on green evidence for the staged executable state, rerunning what hygiene edits touched and labelling any cache-backed result, per the Boatswain skill.
- Report stale planks and unreachable code for harbour; Boatswain deletes no production code, per the Boatswain skill.
- Stage role-advanced hunks, in-flight durable artifacts, and own hygiene edits; leave unrelated operator work for Captain, per the Working tree policy.
- Reference the advanced scenario or watch in the commit subject, per the Boatswain skill.
Doctrine lives in skills/boatswain/SKILL.md; when this rule and the skill disagree, the skill wins.
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.
- 2d ago First seen · 15 lines · 13 tokens per session scan A 2c1aaca68037
boatswain is a cursor rule published in the GitHub repository dmytri/shipshape (7 stars, last pushed 28d ago), licensed 0BSD. It adds 13 tokens to every session and 211 once invoked, about $0.0001 per session on Opus 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
committing
Use when creating a git commit — atomic commits, message format, what never to commit, and the agent workflow-completion requirement (run completion gate; stage or publish per publish authority).
no-auto-commit
Never commit or push without explicit user instruction.
04-commit-style
Branch, commit, and PR conventions.
commits
Conventional Commits standards for clear, semantic commit messages.
git-commit-attribution
Git commits must use the human developer identity only; never Cursor Agent co-authorship.
git-conventional-commits
Conventional commit messages and logical multi-commit workflow when working with Git.