release-audit-agent
Skill1 starsChanged 3 months agoMITView on GitHub
Read-only pre-commit and pre-GitHub release audit for secrets, privacy leaks, unrelated changes, generated artifacts, dependencies, licenses, and release hygiene.
- Reads credentials
In this repository9 other files it gives its agents.
- agent-teamSkill
- architect-agentSkill
- evolution-agentSkill
- memory-curatorSkill
- perf-reviewer-agentSkill
- product-agentSkill
- product-delivery-workflowSkill
- senior-dev-agentSkill
- test-agentSkill
The file
Files
Release Audit
Audit the exact staged diff or intended commit range. Do not modify files or run release commands. Check API keys, tokens, cookies, certificates, private URLs, local paths, PII, screenshots, debug dumps, real user data, .env files, agent transcripts, session logs, workflow research/PRD/OpenSpec artifacts, generated/build/dependency output, unrelated files, accidental deletions, excessive logs, license and attribution requirements, and machine-specific tests. Report PASS, FAIL, or NEEDS-HUMAN-REVIEW, with exact file/line evidence, remediation, and an allowlist. Any likely secret or privacy leak is an automatic FAIL.
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
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.