review ยท diff
git:20261022.7572c8a to git:20261107.e3d6154
12 added, 27 removed. Audit A to A.
What this update changes in the checks
No check changed: every fixed check gives the same answer before and after this update.
A tripped check is a label, not a verdict: read the matched text and the lines below. This week's updates that newly trip a check.
---
name: review
- description: Use when asked for a read-only review of code, documentation, configuration, or workflows. Returns evidence-backed decisions without editing.
+ description: Use when asked for a read-only review of code, documentation, configuration, or workflows.
---
# Review
- Review the requested change without editing it. The goal is a trustworthy merge decision, not the longest list of findings.
-
- ## Evidence
-
- Read the full diff against the supplied base, including how the changed files depend on each other. A finding needs a reachable failure scenario, grounded in something you inspected or ran. Judge materiality against the supplied intent and threat model. A departure from a repository rule is evidence, not automatically a blocker.
-
- Probe as much as you need, but don't modify the shared checkout. Put instrumented probes in a disposable worktree. If you were given a gate result for the exact head, don't rerun the full gate, and use focused probes instead.
-
- ## Lenses
-
- When you're given a lens, report only its failure class and respect its exclusions. Within your lens, go through every surface it owns rather than sampling. Read files outside the lens when they prove an in-lens finding.
-
- ## Decisions
-
- Give each finding exactly one decision:
+ Review the change without editing it, so that someone can decide whether to merge it. Read the whole diff against the base you were given. If you need to change files to test something, do it in a disposable worktree. If you were given a gate result, don't rerun the gate.
- - `block`: demonstrated, within the intent, material under the threat model, and serious enough to stop this merge.
- - `defer`: real and actionable, but outside this pull request or below the merge bar.
- - `discard`: refuted, speculative, already accepted, or not worth scheduling.
- - `ask`: the repository can't choose between materially different, durable product or architecture outcomes, and choosing wrong would be expensive to reverse.
+ Report a problem only when you can show how it would happen, from something you read or ran. Judge how much it matters against the stated intent, usually the pull request's description. Breaking a repository rule is evidence, not a blocker by itself.
- Reserve `ask` for that case, and decide inferable or reversible choices yourself. Recommend the smallest correction within scope, and defer optional machinery.
+ If you're assigned one kind of failure, check everything that could fail that way and report nothing else.
- Also record each finding's `impact`: `breakage`, `weakening`, or `polish`. This is the consequence if the change ships as it is, not the size of the fix.
+ Give each finding its file and line, what goes wrong, and one label:
- Documentation, comments, or instructions that break the documentation rule, whether the diff adds them or leaves them stale, are `block` findings with impact `polish`. Quote the passages to cut.
+ - `block`: you showed it can happen, and it's bad enough to stop this merge.
+ - `defer`: it's real, but it shouldn't stop this merge. Say whether someone would run into it.
+ - `ask`: only a person can choose, because the options are durable product or architecture directions that are expensive to reverse.
- ## Test recommendations
+ Leave out anything you refuted or that isn't worth doing.
- Recommend at most one minimal regression test per failure class, preferably by extending an existing test. Propose browser tests only for browser-specific behavior, and never a new fixture or test mechanism for a single finding.
+ Recommend the smallest fix and a regression test that fails without it.
- ## Output
+ Quote any documentation or comment that breaks the documentation rule under `Cuts`. A cut doesn't block, but it gets made before the merge. Text that would lead a reader into a real failure, such as a wrong command, is a finding instead.
- Group findings by `block`, `ask`, `defer`, and the `discard` decisions worth keeping on record. If nothing qualifies, say so and summarize the surfaces you inspected and the focused checks you ran.
+ If you have no findings, say what you checked.