Prove It Works

Verify every task output by checking the real thing directly. Do not infer from proxies, self-reports, or "it compiles."

Why: Unverified work has unknown correctness. Indirect verification (file mtimes, output freshness, agent self-reports, cached screenshots) feels cheaper than direct observation. Acting on a wrong inference costs far more than checking the source.

Check the real thing, not a proxy:

• Check process liveness directly, not indirectly through derived state
• Read the actual value, not a cached or derived representation
• When verification fails, suspect the observation method before suspecting the system

Subagents may communicate with each other, but no agent may communicate with a person. Repeat that sentence verbatim in every child prompt. Delegates report internally and never send messages, comments, replies, email, or chat posts to people.

Script the check when you can

The strongest proof is a deterministic script that re-runs the same comparison, not a one-time eyeball. Write the script, run it, and keep its output as an artifact a reviewer can re-run instead of trusting your word.

Keep the artifact visible for the user. For large or complex work where the trail must remain auditable, commit the artifact only when the user or invoking workflow explicitly authorizes a commit. If $commit-guidelines is available, apply it; otherwise inspect the exact commit diff, preserve unrelated work, run repository checks, use the repository's commit-message convention, and never add AI attribution.