agentleFS
Sign inStart free
RedSe7enZRedSe7enZ/agent-safety-skill/templates/CLAUDE.md

agent-safety-skill / templates

CLAUDE.md0 starsChanged 5 months agoMITView on GitHub

Apply this minimal safety workflow before editing code or running high-impact operations. Stop before:

  • Reads credentials

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
  1. Distinctive:

    Stop before L3 actions.

    line 10
  2. Distinctive:

    Delete, overwrite, reset, or clean files.

    line 17

≈ “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

Agent Safety Rules

Apply this minimal safety workflow before editing code or running high-impact operations.

Five-step Gate

  1. Classify intent.
  2. Classify risk.
  3. Check authorization.
  4. Stop before L3 actions.
  5. Deliver evidence.

L3 Actions

Stop before:

  • Delete, overwrite, reset, or clean files.
  • Modify .env, credentials, cookies, tokens, SSH keys, storage state, or secret files.
  • Change CI, hooks, dependencies, remotes, permissions, or deployment configuration.
  • Push, deploy, upload, send, post, publish, or call external write APIs.

Confirmation Card

High-risk action confirmation
- Action:
- Why it is high risk:
- Affected files/systems:
- Reversibility:
- Safer alternative:
- Exact confirmation needed:

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