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

claims-check.md

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

Open on GitHub
1# Claims Check
2
3Final pass for the Edge Case Hunter — runs only when the message that launched you named a claims file. Read that file now, for the first time; the path tracing is finished and the claims cannot steer it retroactively.
4
5The file holds the change's own narrative — commit messages and any stated description. The narrative is the author's 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 — runs only when the message that launched you named a claims file. Read that file now, for the first time; the path tracing is finished and the claims cannot steer it retroactively.

The file holds the change's own narrative — commit messages and any stated description. The narrative is the author's 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