safe-operator
Skill0 starsChanged 4 months agoMITView on GitHub
Use before external, credentialed, financial, destructive, installation, deployment, publishing, or production-affecting actions.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- context-hydrationSkill
- operator-heartbeatSkill
- project-bootstrapSkill
- session-continuitySkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Read CLAUDE.md authority rules and config/operator_profile.json.
- Distinctive: line 13
If approval is required, present a preview and ask one precise yes/no question.
- Distinctive: line 14
Verify the result from evidence, not assumption.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill 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
Safe Operator
- State the exact proposed action, target, affected data/system, and whether it is reversible.
- Read
CLAUDE.mdauthority rules andconfig/operator_profile.json. - Classify the action:
- local read/draft/reversible project edit: may proceed
- external, credentialed, financial, destructive, install, publish, deploy, or production: approval required
- If approval is required, present a preview and ask one precise yes/no question. Do not act until the operator explicitly approves that exact action.
- Verify the result from evidence, not assumption.
- Append the action and result to
state/ACTION_LOG.md; never log secrets.
Approval to plan or draft is never approval to execute or send.
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.

