Verification before completion
No assertions without fresh verification evidence.
Gate
Do not claim completion until you have run the relevant check and seen successful output in this session.
Required evidence
| Claim | Minimum evidence |
|---|---|
| Tests pass | Test command output showing pass |
| Build succeeds | Build command exit 0 + output |
| Bug fixed | Reproduction steps pass after fix |
| Lint clean | Linter output on changed files showing zero errors |
| Test guards behavior X | The test fails when X is broken (bug reintroduced or mutated), then passes |
Process
- Identify the command that proves the claim
- Run it (fix failures; do not lower the bar)
- Read output — confirm success, not absence of errors
- Only then state completion
Red flags — stop and verify
- Using "should", "probably", "seems to"
- Reporting success before running the command
- Trusting a prior run after code changed
- "I'm confident" without command output
Short form
CLAIM: [what you want to assert]
EVIDENCE: [command just run]
OUTPUT: [relevant success lines]
VERDICT: [claim supported only if output matches]
Keep this gate for every "done" statement.