check

# check "Check" is the expeditor's call: every plate gets looked at before it leaves the pass. Not the cook's word that it's right, not how it looked ten minutes ago - this plate, looked at now. This skill is that look, applied to any claim of done: run the thing, read the output, then say what the output says. **Core principle:** evidence before claims, always. A completion claim without fresh verification is not optimism, it is a false report. **Violating the letter of this rule is violating its spirit.** ## The iron law No completion claim without fresh verification evidence in this same response. Have not run the proving command since the last change? Then "it works" is not available to you, and neither are its synonyms, paraphrases, or implications. ## Brigade-wired repos: verify with capture When the repo has `.brigade/` (or `brigade status --target .` succeeds), do not run the proving command raw. Route it through Brigade so the exit code becomes a receipt the outcome ledger can score: ```bash brigade work verify run --target . --command "<proving command>" --capture <skill-or-card-id> # or after a brigade run that changed code: brigade outcome capture <skill-or-card-id> --run-receipt latest ``` Then, when GraphTrail/MiseLedger are installed, feed the next run: ```bash brigade receipts export miseledger --target . --new-only --import ``` Raw `pytest` / `npm test` proves the claim for this response but leaves Brigade dormant (`outcome rank` says "ranking: none...