agentsclimarketplace

Vd claim ledger

Skill jpoindexter/verified-done/skills/vd-claim-ledger

Always-on skill pack that stops AI coding agents from claiming work is done when only the code path (not the real behavior) was verified. Portable SKILL.md for Claude Code, Codex, Cursor, and any agent.

Install
npx -y skills add jpoindexter/verified-done --skill vd-claim-ledger

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Before any completion or success claim, build a claim→evidence ledger. Tag each sub-claim ✅ executed (ran it, saw the output), ◐ code-path (read the code, did not run), or ○ assumed, and state explicitly what each piece of evidence does NOT establish. Only ✅ across every Done criterion counts as done. Use whenever you're about to say something works, is wired, passes, or is complete.

SKILL.md

2.2 KB, as published. Nobody here has run it

The Claim → Evidence Ledger

Separate each claim from the evidence that backs it, and grade the evidence honestly. This is the exact move that turns an over-claim into the truth — the transcript that motivated this pack did it as an A/B/C list.

The three grades

GradeMeansEarns "done"?
executedYou ran the real path and observed the expected resultYes
code-pathYou read the code / traced the logic; it should work — not runNo
assumedInferred from a related fact, a convention, or "looks right"No

Build it before you claim

For each Done criterion, write one line:

A. agent loads SOUL.md and runs as Principal Design Engineer   ◐ code-path — not run
B. agent, given "audit stripe.com", calls audit_site + reports ○ not run
C. design engine round-trips over MCP                          ✅ ran tools/call over stdio

Then add, for every ✅, what it does NOT establish:

  • "C proves the engine is exposed over MCP. It does NOT exercise the agent loop or the persona — the MCP server calls the tool directly, with no system prompt and no agent deciding to call it."

The verdict rule

  • Done only when every criterion is ✅.
  • Any ◐ or ○ on a Done criterion → not done. Either go execute it ([[vd-run-the-real-path]]) or report the gap ([[vd-report-the-gap]]).
  • A pile of ✅ on adjacent claims never sums to a ✅ on the real one ([[vd-plumbing-vs-behavior]]).

Why grade the good news too

The danger isn't the ○ you know is shaky — it's the ✅ you over-read. Stating what a green result does NOT prove is what catches "I verified the plumbing and called the feature done." Governed by [[vd-done-is-executed]].

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.