agentleFS
Sign inStart free
CDSecurityCDSecurity/cdsecurity-skills/CLAUDE.md

cdsecurity-skills

CLAUDE.md52 starsChanged 7 months agoMITView on GitHub

Instructions for Claude when contributing to this repository. A library of Claude Code skills for smart contract security, built by CD Security. Each skill is a self-contained capability in its own directory.

The file

We split this CLAUDE.md into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Keep SKILL.md under 500 lines — use references/ for agent-specific instructions.

    line 32
  2. Distinctive:

    No gas optimization checks — out of scope for audit preparation.

    line 33
  3. Distinctive:

    No vulnerability analysis — agents must not perform security assessments.

    line 34
  4. Distinctive:

    Every FAIL finding must include a specific, actionable fix.

    line 35
  5. Distinctive:

    Do not commit secrets, API keys, or personal data.

    line 36
  6. Distinctive:

    Test changes against both eval projects (Hardhat + Foundry) before submitting.

    line 37

≈ “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.

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

CLAUDE.md

Instructions for Claude when contributing to this repository.

What This Repo Is

A library of Claude Code skills for smart contract security, built by CD Security. Each skill is a self-contained capability in its own directory.

Structure

audit-prep/              # Solidity audit preparation (Foundry/Hardhat)
  SKILL.md               # Orchestrator
  VERSION                # Skill version
  references/            # Agent instructions and shared rules
    agents/              # Per-agent instructions (testing, source, infra)
    shared-rules.md      # Common output format for agents
  evals/                 # Test cases and grading scripts

rust-audit-prep/         # Rust/Solana audit preparation (Anchor/native)
  SKILL.md               # Orchestrator
  references/            # Agent instructions, checklist, shared rules
    agents/              # Per-agent instructions (testing, source, infra)
    checklist.md         # Full check reference
    shared-rules.md      # Common output format for agents
    report-template.md   # Detailed report template

Rules

  • One skill, one purpose.
  • Keep SKILL.md under 500 lines — use references/ for agent-specific instructions.
  • No gas optimization checks — out of scope for audit preparation.
  • No vulnerability analysis — agents must not perform security assessments.
  • Every FAIL finding must include a specific, actionable fix.
  • Do not commit secrets, API keys, or personal data.
  • Test changes against both eval projects (Hardhat + Foundry) before submitting.

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