safety-preflight
Skill0 starsChanged 37 days agoMITView on GitHub
Run a deliberate safety preflight before a risky or irreversible change.
In this repository8 other files it gives its agents.
- browser-qaSkill
- compact-checkpointSkill
- evidence-completionSkill
- jev-judgeSkill
- rule-rubricSkill
- seo-auditSkill
- steer-queueSkill
- targeted-file-relevanceSkill
The file
We split this skill 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 13
Check for secret exposure, personal data, network calls, destructive commands, and publication side effects.
- Distinctive: line 17
Do not treat this rubric or the plugin hook as proof of safety.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Perform a safety preflight for: $ARGUMENTS
- State the intended outcome in one sentence.
- List the exact resources that may change: files, branches, services, data, or accounts.
- Separate reversible operations from irreversible or costly operations.
- Identify missing authorization, credentials, backups, rollback paths, and scope boundaries.
- Check for secret exposure, personal data, network calls, destructive commands, and publication side effects.
- Propose the smallest reversible first step.
- End with one verdict:
PROCEED,ASK, orBLOCK, followed by concrete reasons.
Do not treat this rubric or the plugin hook as proof of safety. Inspect the actual command and target.
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.