claude-security-kit
CLAUDE.md0 starsChanged 5 months agoMITView on GitHub
This repo is a Claude Code plugin. It provides: - skills/security-scan/: a skill that orchestrates open-source security scanners over the current repo and writes security-scan-report.md. The roster, install commands, and licenses are in skills/security-scan/reference.md. Read that file before running the skill. - agents/rls-policy-reviewer.md: a read-only Postgres RLS auditor agent. - templates/rls/ and docs/supabase-data-api-lockdown.md: the RLS lockdown kit the agent references. - Never install a scanner without asking the user first. - Never report "no vulnerabilities" when a tool was skipped.…
In this repositoryOne other file it gives its agents.
- security-scanSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Never install a scanner without asking the user first.
- Distinctive: line 16
Never report "no vulnerabilities" when a tool was skipped.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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.
Files
claude-security-kit
This repo is a Claude Code plugin. It provides:
skills/security-scan/: a skill that orchestrates open-source security scanners over the current repo and writessecurity-scan-report.md. The roster, install commands, and licenses are inskills/security-scan/reference.md. Read that file before running the skill.agents/rls-policy-reviewer.md: a read-only Postgres RLS auditor agent.templates/rls/anddocs/supabase-data-api-lockdown.md: the RLS lockdown kit the agent references.
Behavior the skill must keep
- Never install a scanner without asking the user first.
- Never report "no vulnerabilities" when a tool was skipped. Report what ran, what was skipped and why, and the resulting coverage gaps.
- Report the resolved version of each tool that runs, and prefer pinned versions.
House style for docs
User-facing copy in this repo avoids em dashes and AI-sounding filler, and states tool limitations plainly. Keep that voice in any README or doc changes.
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.