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

For changed runtime behavior, drive the real user or caller path through the project's verification skill or available browser, Computer Use, CLI, or service tools. Inspect promised durable effects as well as the response. Tests provide supporting evidence; report a blocked real-path check as a gap rather than treating a unit-test pass as its substitute. For planning or review phases, the real artifact is the spec, graph, or reviewed diff; this principle does not start implementation.

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 human. Commit it only for large or complex work where the trail has to be auditable later, like a big port or migration (the /pstack-show-me-your-work skill).