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/dmytri/shipshapeWrote 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/dmytri/shipshape/crew)<a href="https://agentmods.dev/rules/dmytri/shipshape/crew"><img src="https://agentmods.dev/badge/rules/dmytri/shipshape/crew/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/dmytri/shipshape/crew"><img src="https://agentmods.dev/badge/rules/dmytri/shipshape/crew.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 | $0.00010 | $0.00172 |
| Opus 5.5 | $0.00004 | $0.00069 |
| Sonnet 5.5 | $0.00002 | $0.00034 |
| Haiku 4.5 | $0.00001 | $0.00017 |
Grade A, and why
crew 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.
What it actually says
Crew, before returning:
- Write production code only, and make the smallest change the failing target requires, per the "Write scopes are strict" and "Simplest sufficient change" Articles.
- Annotate every changed seam with
@planks("<step>"), normalized to the inherited Gherkin keyword, per the Planking agreement. - Run the
focusedcommand fromRIGGING.mdon the target and report the fresh result. - Let errors propagate with their original traceback; add no defensive handling the scenario does not require.
- Stop and report when one correction fails, or when the test or spec seems wrong, per the Crew skill.
Doctrine lives in skills/crew/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.
- 1mo ago First seen · 14 lines · 10 tokens per session scan A 82ed8e9e91d0
crew is a cursor rule published in the GitHub repository dmytri/shipshape (7 stars, last pushed 2mo ago), licensed 0BSD. It adds 10 tokens to every session and 172 once invoked, about $0.0000 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
root-cause-first
Require source-level fixes for malformed or polluted domain data.
github-issue-triage
Triage a GitHub issue by verifying all factual claims against running code, assessing roadmap fit, then posting a structured response comment with confirmed findings, stale corrections, a recommendation, and concrete test steps.
error-handling
Use when building error recovery, handling exceptions, designing error flows, or implementing logging for errors — covers retry, circuit-breaker, error wrapping, structured logging.
performance-profiling
Use when diagnosing slow code, high memory usage, or CPU spikes — language-agnostic profiling workflow: form a hypothesis, identify the hot path, benchmark before and after, and interpret profiler output. Includes Python (cProfile, py-spy), Go (pprof), and Node.js (--inspect, clinic.js) tooling.
refactoring
Use before restructuring code — covers behavior-preservation contracts, characterization tests, incremental reversible steps, and protected public contracts. Ensure refactoring remains a code change, not a feature change.
logging
Use when adding logging to an application, reviewing log output, choosing log levels, structuring logs for observability, or configuring logging backends — covers structured logging, YAML config patterns, what NOT to log, and local vs. production output.