agentleFS
enes-alatasenes-alatas/spool/.claude/skills/credential-incident/SKILL.md

credential-incident

Skill48 starsChanged 3 days agoApache-2.0View on GitHub

Use the moment a live credential is in front of you — in a log, a body, a transcript, a screenshot — or one has been posted to GitHub.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    A live credential in front of you is an incident: Stop; do not copy it anywhere.

    line 15

≈ “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.

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

/credential-incident — a live credential in front of you

Moved verbatim from docs/CONVENTIONS.md (#470), which keeps the one-line rule and points here. The rule binds whether or not this skill is loaded.

A live credential in front of you is an incident. Stop; do not copy it anywhere; redact it where you can still reach it; tell the operator privately. The value and the steps that reproduce it never go in the group — that an exposure happened does, because everyone's evidence may carry it. The operator rotates. Whoever found it files the code issue with the value redacted — the fix is public work, the exposure is not.

An issue or comment body is redacted, not rejected: text posted to GitHub is published before anything can run, so the redaction guard in the issue-guards workflow edits the value out and posts what the edit does not fix — the revision history still holds the original, and rotation is not optional. Who deletes the revision depends on who pasted it: a person does it themselves, from the edited menu; a loop cannot, because edit history is read-only in both APIs, so it reports the exposure privately to the operator — what and where, never the value — and the operator deletes it (#206). Both guards read their shapes from scripts/secret-rules.awk; two of those shapes — a loop's bot handle and the group's chat id — apply to bodies only, since in the tree they are configuration and fixture data rather than a quote of the group (#249).

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.