agentleFS
Sign inStart free
sdvsignalsdvsignal/done-needs-proof/skills/prove/SKILL.md

prove

Skill0 starsChanged 49 days agoMITView on GitHub

Use before telling the user that work is done, fixed, deployed, merged, or that tests pass. Pick the smallest check that proves the claim, run it after the last edit, and quote its output next to the claim. Say UNVERIFIED for anything you could not check.

13 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Quote the output: Put the one or two lines that prove it next to the claim.

    line 22
  2. Very specific:

    Say what you could not check: If something needs a device, a login or a human, write UNVERIFIED: and what would verify it.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “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

Prove it before you say it

A completion claim is only as good as the evidence next to it. Before you write "done", "fixed", "live", "merged" or "tests pass":

  1. Name the claim. What exactly are you about to say is true?

  2. Pick the smallest check that would fail if the claim were false.

    ClaimCheck
    tests passrun the suite (or the affected file) and keep the summary line
    fixedreproduce the original failure, show it no longer fails
    deployed / livecurl -sI <url> and keep the status line
    merged / pushedgit log origin/<branch> --oneline -3
    buildsrun the build and keep the last lines
  3. Run it after your last edit. A check that ran before the final change proves nothing about the final code.
  4. Quote the output. Put the one or two lines that prove it next to the claim.
  5. Say what you could not check. If something needs a device, a login or a human, write UNVERIFIED: and what would verify it. Do not round it up to "done".

Why the Stop hook might block you

This plugin also installs a Stop hook. If your final message claims completion and no matching check ran in the same turn after your last edit, the hook blocks the stop and tells you which check is missing. Run the check and restate the result, or reword the message so it says what is still unverified. It fires once per stop; it will not loop.

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