agentleFS
Sign inStart free
pinexaipinexai/claude-code-skills/run-receipt/SKILL.md

run-receipt

Skill1 starsChanged 4 months agoMITView on GitHub

Use this skill at the end of any multi-step task — one that touched several files, ran commands, or made claims about tests/builds passing. Triggers include finishing such a task, "did it actually pass", "show me what changed", "what did you actually verify", or "prove it". Do NOT use this skill for a single trivial edit (one file, no commands run) — the receipt exists to make multi-step work auditable, not to add ceremony to small changes.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. frankxai/skills★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

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
  1. Very specific:

    Show test/build status before → after: Run the actual before and after states through scripts/diff_test_runs.py when two test-run outputs …

    line 30
  2. Distinctive:

    Never report a test as passing without showing the exact command and its actual result.

    line 42
  3. Distinctive:

    Don't backfill verification after the fact to make the receipt look cleaner — if something wasn't checked during the task, it belongs in …

    line 48

≈ “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

Run Receipt

When this fires

Agentic work can look complete without being complete — a summary that says "tests pass" without showing the command, or a claim about behavior that was never actually executed. This skill closes that gap: after a multi-step task, produce a receipt that separates what was actually run and observed from what was merely asserted.

Protocol

  1. List files touched — every file created, edited, or deleted during the task, with a one-line description of the change.
  2. List commands run — the exact commands executed (tests, builds, linters, scripts), not a paraphrase.
  3. Show test/build status before → after. Run the actual before and after states through scripts/diff_test_runs.py when two test-run outputs are available, to get an accurate pass/fail delta rather than an eyeballed one.
  4. Separate unverified claims. Anything asserted during the task that was not actually executed or checked — "this should also fix Y", "this is probably faster", "this covers the edge case too" — goes in its own section, explicitly labeled as unverified. This section is mandatory even when empty; write "None" rather than omitting it.

Hard rules

  • Never report a test as passing without showing the exact command and its actual result. "Tests pass" with no command shown is not a valid receipt line.
  • The unverified-claims section must always be present, even when there's nothing in it — an omitted section reads as "I checked everything," which is exactly the false confidence this skill exists to prevent.
  • Don't backfill verification after the fact to make the receipt look cleaner — if something wasn't checked during the task, it belongs in Unverified, not quietly moved into Verified.

Output

## Files touched
- <path> — <what changed>

## Commands run
- `<exact command>` — <result summary>

## Test/build status
Before: <status, from actual command output>
After:  <status, from actual command output>
<diff_test_runs.py output when applicable>

## Unverified claims
- <claim asserted but not actually checked>
(or: None)

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