agentleFS
Sign inStart free
ryanmacleanryanmaclean/skills/gh-auth/SKILL.md

gh-auth

Skill1 starsChanged 50 days agoMITView on GitHub

Enforce safe authentication behavior for GitHub and other CLIs. Use when handling credentials, checking auth status, or debugging agent auth failures so login churn and lockouts never happen.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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
  1. Distinctive:

    Use this skill whenever auth is involved.

    line 8
  2. Distinctive:

    Never run interactive login commands unless the user explicitly asks for login in this turn.

    line 12
  3. Distinctive:

    Never repeat login attempts in a loop.

    line 13
  4. Distinctive:

    If auth status is already healthy, stop there and continue the task.

    line 14
  5. Distinctive:

    Prefer non-interactive credential propagation (env vars, instructions-path policy, secure files) over re-auth.

    line 15
  6. Distinctive:

    If healthy, do not mutate auth state.

    line 20
  7. Distinctive:

    If unhealthy, choose one:

    line 21
  8. Distinctive:

    Use existing token/secret delivery already provided by the operator.

    line 23
  9. Very specific:

    If no non-interactive credential is available, patch issue status to blocked with concise unblock instructions.

    line 43
  10. Distinctive:

    Do not start auth flows from heartbeat loops.

    line 44

≈ “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.

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

gh-auth

Use this skill whenever auth is involved.

Non-negotiable rules

  • Never run interactive login commands unless the user explicitly asks for login in this turn.
  • Never repeat login attempts in a loop.
  • If auth status is already healthy, stop there and continue the task.
  • Prefer non-interactive credential propagation (env vars, instructions-path policy, secure files) over re-auth.

Safe auth flow

  1. Check status only.
  2. If healthy, do not mutate auth state.
  3. If unhealthy, choose one:
  • Continue read-only work without auth.
  • Use existing token/secret delivery already provided by the operator.
  • Mark blocked with exact unblock action.

Allowed checks (read-only)

gh auth status -h github.com || true
git config --global --get credential.helper || true
env | grep -E '^(GH_TOKEN|GITHUB_TOKEN)=' || true

Forbidden by default

  • gh auth login
  • gh auth logout
  • any browser/device-code auth initiation

Paperclip-specific guidance

  • For agent runs, prefer setting adapterConfig.env.GH_TOKEN through the Paperclip API.
  • If no non-interactive credential is available, patch issue status to blocked with concise unblock instructions.
  • Do not start auth flows from heartbeat loops.

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