agentleFS
Sign inStart free
getedgehqgetedgehq/skills/agent-receipt/SKILL.md

agent-receipt

Skill5 starsChanged 11 days agoApache-2.0View on GitHub

Create a compact, evidence-backed proof-of-work receipt for a completed AI agent run. Use when the user wants to summarize what an agent actually built, how long it took, what changed, tests run, interventions, deployment status, or skills used.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 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.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never infer a passed test, deployment, duration, or intervention count.

    line 9
  2. Distinctive:

    Write a local JSON manifest with: project, agent, duration_minutes, interventions, files_changed, tests_passed, tests_total, verification, …

    line 10
  3. Very specific:

    Run scripts/receipt.py <manifest> --out <public-result.json>.

    line 11
  4. Distinctive:

    Keep the source manifest and raw evidence local unless the user explicitly approves publishing selected evidence.

    line 13

≈ “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

Agent Receipt

  1. Gather only evidence available in the current run/repo.
  2. Never infer a passed test, deployment, duration, or intervention count. Use unknown instead.
  3. Write a local JSON manifest with: project, agent, duration_minutes, interventions, files_changed, tests_passed, tests_total, verification, deployed, skills_used, and evidence.
  4. Run scripts/receipt.py <manifest> --out <public-result.json>. The public result contains evidence hashes and counts, never raw evidence values.
  5. Run scripts/render.py <public-result.json> --svg <card.svg> [--png <card.png>].
  6. Keep the source manifest and raw evidence local unless the user explicitly approves publishing selected evidence.
  7. Publishing is a separate external action. Confirm destination and visibility immediately before uploading unless the current request already authorizes it.

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