Verify This
Verification is not a recap. It proves or disproves a specific claim with repeatable evidence.
When To Use
- The user asks "verify this", "prove it works", "did this fix it", or "show me the evidence".
- A bug fix needs a before/after repro.
- A UI, CLI, API, performance, or memory claim needs measurement.
- A test passes but the user-visible behavior still needs confirmation.
Do not use this for vague claims like "the code is cleaner". Ask for a measurable claim first.
Workflow
- Restate the claim in falsifiable form: condition, metric, and threshold.
- Pick the smallest local surface that can disprove it.
- Capture a baseline from the old state: merge base, parent commit, failing branch, or current broken repro.
- Capture treatment from the changed state with the same command, data, warmup, and environment.
- Compare raw artifacts: numbers, screenshots, terminal transcripts, HTTP responses, profiles, heap snapshots, or test output.
- Return exactly one verdict:
VERIFIED, NOT VERIFIED, or INCONCLUSIVE.
Local Surfaces
- Code behavior: focused unit/integration tests or a minimal repro script.
- CLI/TUI behavior: terminal transcript or demo recording.
- UI behavior: screenshots, accessibility snapshots, or browser traces (playwright-cli when available).
- API behavior: local HTTP/RPC request and response diff.
- Performance: same-machine baseline/treatment timings or CPU profiles.
- Memory: heap snapshots before and after the suspected operation.
Artifact Layout
When safe to write artifacts:
<scratch-dir>/verify-this/<claim-slug>/ # the harness scratchpad when it provides one, else /tmp
├── claim.md
├── timeline.md
├── baseline/
├── treatment/
├── diff/
└── verdict.md
If artifacts may contain sensitive code, prompts, screenshots, HTTP bodies, or heap data, keep only the minimal inline evidence unless the user agrees to disk storage.
Verdict Rules
VERIFIED: baseline and treatment differ in the predicted direction, by the claimed threshold, with no obvious confound.NOT VERIFIED: the behavior is unchanged, moves the wrong way, or misses the threshold.INCONCLUSIVE: no valid baseline, noisy signal, failed measurement, or an environment difference invalidates the comparison.
Output
Use this shape:
VERIFIED | NOT VERIFIED | INCONCLUSIVE
Claim: <falsifiable claim>
Evidence:
<metric/artifact>: baseline=<...>, treatment=<...>, delta=<...>, threshold=<...>
Reasoning:
<one tight paragraph naming the evidence and any confounds>
Do not soften a negative result. A clear NOT VERIFIED is useful.
1---2name: verify-this3description: Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.4---56# Verify This78Verification is not a recap. It proves or disproves a specific claim with repeatable evidence.910## When To Use1112- The user asks "verify this", "prove it works", "did this fix it", or "show me the evidence".13- A bug fix needs a before/after repro.14- A UI, CLI, API, performance, or memory claim needs measurement.15- A test passes but the user-visible behavior still needs confirmation.1617Do not use this for vague claims like "the code is cleaner". Ask for a measurable claim first.1819## Workflow20211. Restate the claim in falsifiable form: condition, metric, and threshold.222. Pick the smallest local surface that can disprove it.233. Capture a baseline from the old state: merge base, parent commit, failing branch, or current broken repro.244. Capture treatment from the changed state with the same command, data, warmup, and environment.255. Compare raw artifacts: numbers, screenshots, terminal transcripts, HTTP responses, profiles, heap snapshots, or test output.266. Return exactly one verdict: `VERIFIED`, `NOT VERIFIED`, or `INCONCLUSIVE`.2728## Local Surfaces2930- Code behavior: focused unit/integration tests or a minimal repro script.31- CLI/TUI behavior: terminal transcript or demo recording.32- UI behavior: screenshots, accessibility snapshots, or browser traces (playwright-cli when available).33- API behavior: local HTTP/RPC request and response diff.34- Performance: same-machine baseline/treatment timings or CPU profiles.35- Memory: heap snapshots before and after the suspected operation.3637## Artifact Layout3839When safe to write artifacts:4041```text42<scratch-dir>/verify-this/<claim-slug>/ # the harness scratchpad when it provides one, else /tmp43├── claim.md44├── timeline.md45├── baseline/46├── treatment/47├── diff/48└── verdict.md49```5051If artifacts may contain sensitive code, prompts, screenshots, HTTP bodies, or heap data, keep only the minimal inline evidence unless the user agrees to disk storage.5253## Verdict Rules5455- `VERIFIED`: baseline and treatment differ in the predicted direction, by the claimed threshold, with no obvious confound.56- `NOT VERIFIED`: the behavior is unchanged, moves the wrong way, or misses the threshold.57- `INCONCLUSIVE`: no valid baseline, noisy signal, failed measurement, or an environment difference invalidates the comparison.5859## Output6061Use this shape:6263```text64VERIFIED | NOT VERIFIED | INCONCLUSIVE65Claim: <falsifiable claim>6667Evidence:68<metric/artifact>: baseline=<...>, treatment=<...>, delta=<...>, threshold=<...>6970Reasoning:71<one tight paragraph naming the evidence and any confounds>72```7374Do not soften a negative result. A clear `NOT VERIFIED` is useful.
davesnx