verification-before-completion

Identify the command that proves your claim, run it fresh and in full, read the complete output including exit codes, and only then state the result with that evidence. Never claim success based on previous runs or assumptions.

Sufficient evidence is the actual test command output showing zero failures from a fresh run in the current session. Prior runs, partial checks, or statements like "should pass" do not qualify as verification.

Linters check style and syntax patterns but do not verify compilation. Claiming a build succeeds requires running the actual build command and confirming it exits with code 0.

Use the red-green cycle: write the test, run it to confirm it passes, revert the fix and confirm the test fails, then restore the fix and confirm it passes again. A test that only passes once proves nothing.

No, agent success reports must be verified independently. Check the version control diff to confirm actual changes were made and run the relevant verification commands yourself before reporting completion.

Apply it before any success or completion claim, expression of satisfaction, commit, pull request, task handoff, or delegation. The rule covers exact phrases, paraphrases, and any implication that work is correct or done.