/maestro-verify

name: maestro-verify
description: Verify and close - cross-check coverage, run the VERIFY table, deliver the verdict, harvest durable lessons into decisions, close the bundle, and never claim remote state from local evidence.
review-date: 2026-11-28

<!-- maestro-skill-version: dev -->

maestro-verify

Use for verification and close. Read [WORKFLOW.md](~/maestro/WORKFLOW.md) for testing, recovery, authorization, and completion rules. Delivery actions such as commit, install, push, or release remain separate gates.

Precondition: an open bundle with a drafted VERIFY.md. Without a bundle, verify inline and close a tracked item with `maestro work done`; an untracked quickfix needs no record. This skill's table pass is for Full work. The evidence-layer vocabulary below still applies to any claim at any tier.

Evidence layers

Proof follows five links. Claim only as far as the last proven link.

• `source` - source-level tests, lint, type checks, or direct inspection.
• `artifact` - the built or packaged output is present and has been read back.
• `installed` - the installed stamp, version, or files match the intended artifact.
• `live` - the running process, pid, or active runtime matches the installed layer.
• `journey` - the real user path reaches the observable outcome end to end.

The repository's `verify-<repo>` skill is the route to `live` and `journey`; `maestro recipe show verification-skill` creates or maintains it.

"Tests pass" is a source claim. A claim that touches install or runtime must include a readback at that layer. A suite that is green only on this machine is not a `source` claim about the repo: before any commit, release, or handback gate, re-run the touched suite with the developer environment removed (`HOME=$(mktemp -d)`, `env -u HERDR_ENV`). A test that reads the installed copy, the room, or a home config passes for you and fails in CI. Every proof and VERIFY result lists untested links explicitly as `NOT TESTED`, never by omission:

proof: "suite 135 pass @ a52bd4a7 (source); runtime stamp readback a52bd4a7 (installed); live: NOT TESTED"
Assumptions not verified: None
Residual risks: None

Verify

• Cross-check the evidence plan against acceptance and relevant risks. Map

existing tests, necessary new checks, readbacks, or baselines to VERIFY.md. A missing behavior check is a gap; the absence of a newly written test is not.

• Run every VERIFY.md scenario against its work item's acceptance/claims and

fill its unit, live, and perf cells with evidence or `n/a: <reason>`; run each anti-goal check (grep, diff, readback). Stamp each row with its commit and the pass with its date, then run `maestro bundle check <id> --final`. Results hold this run only: a re-run replaces prior results wholesale, and a failed pass leaves its one-line `failed:` note on the work item, never accumulated rounds in VERIFY.md. Apply [Recovery and verification](~/maestro/WORKFLOW.md#recovery-and-verification) when a scenario cannot run as written: document and execute an equivalent check without changing acceptance, or report the gap if equivalence is unknown.

• Run the repo's checks for the touched surface (tests, lint, types, build),

then freeze and review the task-owned diff: every changed line traces to the SPEC's scope or a linked work item; nothing unrelated is staged.

• For a concrete assertion-strength concern, inspect whether the existing

check distinguishes the approved outcome from the suspected wrong behavior. A focused mutation can establish that; restore it before continuing. Do not expand verification into an unrelated edge-case or coverage campaign.

• Re-read the user's exact delivery authority and target before any gate.
• Select one legal next gate at a time: final verification, independent QA or

witness, scoped commit, local install, external delivery, or stop. Do not bundle gates whose authority differs.

• Read back the actual result: test output, commit hash, installed version. A

started or interrupted command is not delivery evidence.

For substantial diffs, verify in a fresh context: dispatch a subagent that reads only the bundle and the diff - the implementer verifying their own work invites confirmation bias. The subagent never fixes anything: mutants it flips are reverted before reporting, and on FAIL it records the verdict and stops; routing back to implementation belongs to the parent turn that holds the user's ask. A subagent that fails to start or report is a dispatch failure, not evidence: run the checklist in this session instead of polling for it.

On FAIL, leave `maestro work note <id> "failed: <one line>"` and return the evidence to the implementation owner. Use the shared recovery rule to choose the next action from the cause, not a failure count. Read prior failed notes so a new session does not repeat the same uninformative attempt.

Read-only review method: [references/audit.md](references/audit.md). When the failure location is unclear, follow [references/triage.md](references/triage.md).

Red flags

| The thought | The reality | |---|---| | "It obviously passes - running it is a formality" | Scenarios exist because "obviously" has been wrong before. Run every one and record the output. | | "The scenario command is stale, so I can skip the check" | Repair it or demonstrate an equivalent measurement; preserve acceptance and record the change. | | "The mutant survived, but the code is clearly fine" | If the mutant violates acceptance, the check is weak; report the gap rather than filling PASS. | | "I wrote this diff - I know it works" | That is the confirmation bias the fresh-context rule exists for. | | "I'll just fix this small failure while I'm verifying" | Verify delivers a verdict, never fixes. A FAIL routes back to the playbook's fix step. |

Learn, then close

Before closing, harvest what outlives the bundle ([references/learning.md](references/learning.md)): a verified correction or