Skill Tracer
Skills › BMAD Method › bmad-build › claims-check.md

claims-check.md

14 lines · skills/bmad-build/references/claims-check.md at bd70c64

Open on GitHub
1# Claims Check
2
3Final pass for the Edge Case Hunter. Read the claims file named in the message that launched you now, for the first time; the path tracing is finished and the claims cannot steer it retroactively.
4
5It is the plan the change was built from. Read only its `## Intent` and `## Tasks & Acceptance` sections — the claims live there; ignore the rest of the file. The plan is the change's own account of itself: testimony, not evidence — a claim repeated in a code comment is still the same claim, not confirmation. Extract each checkable claim — what the change does, what it preserves, ordering, arithmetic, and parity with existing code ("exactly as X does") — then try to falsify each one against the code you have already traced. Where your trace is not enough to decide, read the code that decides it: the compared-to function, the actual callee, the state the claim assumes.
6
7Append one finding per falsified claim to the same JSON array, with the four standard fields plus:
8
9- `kind`: `"claim"`
10- `confidence`: `"high"`, `"medium"`, or `"low"`
12For a claim finding the standard fields read as: `location` = where the code contradicts the claim; `trigger_condition` = the claim, quoted or tightly paraphrased; `guard_snippet` = what the code actually does; `potential_consequence` = what goes wrong for someone who believed the claim.
14Verified claims produce nothing. Add nothing if nothing is falsified.

Claims Check

Final pass for the Edge Case Hunter. Read the claims file named in the message that launched you now, for the first time; the path tracing is finished and the claims cannot steer it retroactively.

It is the plan the change was built from. Read only its ## Intent and ## Tasks & Acceptance sections — the claims live there; ignore the rest of the file. The plan is the change's own account of itself: testimony, not evidence — a claim repeated in a code comment is still the same claim, not confirmation. Extract each checkable claim — what the change does, what it preserves, ordering, arithmetic, and parity with existing code ("exactly as X does") — then try to falsify each one against the code you have already traced. Where your trace is not enough to decide, read the code that decides it: the compared-to function, the actual callee, the state the claim assumes.

Append one finding per falsified claim to the same JSON array, with the four standard fields plus:

  • kind: "claim"
  • confidence: "high", "medium", or "low"

For a claim finding the standard fields read as: location = where the code contradicts the claim; trigger_condition = the claim, quoted or tightly paraphrased; guard_snippet = what the code actually does; potential_consequence = what goes wrong for someone who believed the claim.

Verified claims produce nothing. Add nothing if nothing is falsified.

Raw lines 1 to 14