verify-this

# Verify This Verification is a falsifiable comparison, not a recap of what the agent believes it changed. Turn one claim into a measurable check and preserve enough evidence for another agent to repeat it. ## Workflow 1. Restate the claim as a condition, metric, and threshold. If the claim cannot be measured, ask for a measurable form or classify it as `INCONCLUSIVE`. 2. Select the smallest local surface that can disprove it. 3. Capture a baseline from the parent commit, merge base, current failing reproducer, or unchanged fixture. 4. Capture treatment with the same command, data, warmup, environment, and measurement method. 5. Compare raw artifacts: test output, timings, screenshots, HTTP responses, traces, profiles, or heap snapshots. Do not compare summaries alone. 6. Return exactly one verdict: `VERIFIED`, `NOT VERIFIED`, or `INCONCLUSIVE`. ## Evidence Contract Record: - claim and threshold; - revision or baseline identity for both runs; - exact commands and input fixture; - environment differences and skipped checks; - artifact paths or hashes, with sensitive payloads kept outside public Git; - the verdict and one short explanation of confounders. For durable project work, use the repository's existing proof artifact location, for example `.agent/tasks/<task-id>/verification/<claim-slug>/`. Temporary or sensitive evidence may stay outside the repository; retain only safe metadata and hashes in the project. Never put credentials, private prompts, custo...