agentleFS
Sign inStart free
blitzcrieg1blitzcrieg1/agentmetry/.claude/skills/ship-safe/SKILL.md

ship-safe

Skill40 starsChanged 34 days agoApache-2.0View on GitHub

Pre-flight a change before opening a pull request on Agentmetry. Use before committing or opening a PR, when the user says ship it, or to check whether a change is safe to land during the detection freeze.

  • Reads credentials

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. mahik504/orchestra-workflow★ 1same name
    2. HumSaw/shipwright-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the dashboard changed, also cd apps/dashboard && npm run lint && npm run test && npm run build.

    line 42
  2. Very specific:

    If the change touches a number that appears in README.md, the site, or docs/, check the claim tests still pass.

    line 59
  3. Distinctive:

    If the change adds a public claim about the code, add a test that checks it.

    line 63
  4. Distinctive:

    Commit only when the user asks: Run the checks, report the result, wait.

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ship safe

Five checks. The first one is the one that matters, because it is the only failure here that costs four weeks instead of four minutes.

1. Did this touch a frozen file?

git diff --name-only master... | grep -E "detection/(rules|traits|engine)\.py|audit/mitre\.py|policies/detection/manifest\.yaml"

Any output means stop and tell the user. Those files are hashed into the ruleset fingerprint; changing one restarts the dogfood clock, which is at 2 of 4 with an earliest close of 2026-09-04. The freeze lifts 2026-09-05.

Confirm the fingerprint independently, because a file can be touched without the grep catching a rename:

cd apps/orchestrator && .venv/Scripts/python.exe -c "from agentmetry.core.audit.dogfood import ruleset_fingerprint; print(ruleset_fingerprint()[:16])"
# expect 56ad3de1ad8533cf

2. Tests, lint, benchmark

From apps/orchestrator:

.venv/Scripts/python.exe -m ruff check agentmetry tests
.venv/Scripts/python.exe -m pytest -q
.venv/Scripts/python.exe -m agentmetry.cli benchmark

The benchmark must report 0 missed and 0 false positives. A release that cannot detect what it claims to detect is the one release worth blocking.

If the dashboard changed, also cd apps/dashboard && npm run lint && npm run test && npm run build.

3. Secrets and local files

git diff --cached --name-only

Reject: .env, drivers.json, anything under apps/orchestrator/data/, any .jsonl trail, .coverage. .agents/hooks.json holds machine-specific absolute paths and is usually dirty; do not stage it unless the task is hooks.

Scan the diff itself for anything key-shaped before pushing. CI runs gitleaks, but a secret caught after it reaches the remote is already a rotation.

4. Claims still true?

If the change touches a number that appears in README.md, the site, or docs/, check the claim tests still pass. tests/test_readme_claims.py pins corpus counts, CLI coverage of the docs, and the attribution paragraph.

If the change adds a public claim about the code, add a test that checks it. The README once overstated its own weakness for weeks and three audits repeated it.

5. Then open a PR

master is protected: five required checks, enforce_admins on, so a direct push is rejected. Branch, push, open a PR.

Match the commit-message voice in git log: what changed, what was wrong before, what that cost. Not a summary of the diff, which the diff already is.

No em-dashes in anything that will be read publicly.

Rule

Commit only when the user asks. Run the checks, report the result, wait.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free