agentleFS
Sign inStart free
naman10parikhnaman10parikh/fleet-audit/CLAUDE.md

fleet-audit

CLAUDE.md0 starsChanged 12 days agoMITView on GitHub

- The hook. .claude/settings.json runs hooks/prepushscrubhook.py before every Bash command. On a git push it scrubs the committed tree with the patterns file in $FLEETAUDITPATTERNS (or .fleet-audit/scrub-patterns.txt, which git ignores) and blocks the push on a match, naming the pattern number and the file. With no patterns file it lets the push through. The plugin ships the same hook in hooks/hooks.json. - The MCP server. .mcp.json runs the server from GitHub through uvx. To try your local changes, start Claude…

  • Commits and pushes
Create a free account to mount
Files
CLAUDE.md

@AGENTS.md

fleet-audit: notes for Claude Code

  • The hook. .claude/settings.json runs hooks/prepush_scrub_hook.py before every Bash command. On a git push it scrubs the committed tree with the patterns file in $FLEET_AUDIT_PATTERNS (or .fleet-audit/scrub-patterns.txt, which git ignores) and blocks the push on a match, naming the pattern number and the file. With no patterns file it lets the push through. The plugin ships the same hook in hooks/hooks.json.
  • The MCP server. .mcp.json runs the server from GitHub through uvx. To try your local changes, start Claude Code with claude --mcp-config .mcp.dev.json, which runs it from src/.
  • Sub-agents. Hand an audit to readiness-auditor (it changes nothing) and agreed fixes to surface-fixer.
  • Before you finish: python3 -m unittest && python3 evals/run.py, then PYTHONPATH=src python3 -m fleet_audit check . --offline --head, which must show nothing missing.
  • Code style. Standard library only in src/ (the e2b package is optional and used only by sandbox/), files under 400 lines, and planted test strings assembled at run time (see evals/repos.py).
  • No model ID anywhere. fleet-audit calls no model.

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.

Reviews can't be read right now.

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