review-change
Skill0 starsChanged 37 days agoMITView on GitHub
Review a change the way a reviewer who will be held to it does: findings only on the change that introduced the code, verified at its head sha, one finding per thread in Conventional Comments with the defect, file:line, consequence, rule and required behaviour, a two to four line summary that ends in a decision, a mutation check before trusting a test, dependency bumps one at a time, and an adversarial read of your own work before anyone else sees it. Triggers on: "review", "code review", "review this PR", "review this MR", "review the diff", "LGTM?", "is this safe to merge", "self-review", a diff pasted inline, "before I push".
32 other projects use a version of this.
Adopted by
Most recently taken up by
- jorgenschaefer/skillstheir own version, first seen Nov 16, 2026
- MandalorianBatman/austere-axitheir own version, first seen Nov 16, 2026
- Krzysztof318/MailFathomtheir own version, first seen Nov 15, 2026
- CsHeng/agent-skillstheir own version, first seen Nov 9, 2026
- EpicGames/loretheir own version, first seen Nov 9, 2026
- SaKaNa-Y/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use plan-change, implement-change and 7 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
BanKnightSkillplan-change
将已完成 spec/design 的 change 拆成可执行 plan 与 tasks。用户要把设计落成执行计划、任务清单或实现步骤时使用。
Also in 7 projects that use this
Codagent-AISkillimplement-change
Implements an approved change in one continuous session, with tiered test runs. Use when asked to implement a change from its approved definition, or to invoke codagent:implement-change.
Also in 7 projects that use this
MaheshAwasareSkillwrite-runbook
Generate an operational runbook for a service from its code, config, and dependencies — what to do when it breaks, where to look, how to roll back, who to escalate to. Use proactively before a service goes to production, after a major incident, or when handing off operational ownership.
Also in 3 projects that use this
testified-ossSkillincident-triage
Triage production incidents with severity assessment, root cause hypothesis, impact analysis, and escalation recommendations. Use when analyzing outages, errors, or production issues.
Also in 4 projects that use this
srclightSkillrefactor-safely
This skill should be used when the user asks to "refactor", "rename", "move", "change a function signature", "extract a method", "delete unused code", "clean up", or any modification that could break callers or dependents. Provides a pre-change safety checklist using srclight's graph tools to assess blast radius before touching code.
Also in 3 projects that use this
Google CloudSkillopen-pr
Commits local changes to a new Git branch and opens a GitHub pull request through the configured GitHub MCP server. Use when proposing code changes in a new pull request. Don't use for local-only commits without a remote GitHub repository.
Also in 4 projects that use this
Other versions32 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 32
- ben-manes/caffeine★ 18ksame name
- EpicGames/lore★ 9.2ksame name
- maypok86/otter★ 2.7ksame name
- aquaproj/aqua-registry★ 400same name
- Esri/calcite-design-system★ 385same name
- yiming-liao/intor★ 211same name
- gtrabanco/agentic-workflow★ 23same name
- fathomise/MailFathom★ 21same name
- Krzysztof318/MailFathom★ 21same name
- Indium-AI-Labs/indium-agentkit★ 18same name
22 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- cut-ticketsSkill
- decision-recordsSkill
- deep-modulesSkill
- evidenceSkill
- grill-planSkill
- plain-voiceSkill
- plan-projectSkill
- setup-conventionsSkill
- test-firstSkill
- thin-slicesSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 27 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 46
Read the tests first, then run REVIEW-4 on at least one new condition when a suite can run.
- Distinctive: line 55
Write the findings (REVIEW-2), order them by payback, then the summary (REVIEW-3).
- Distinctive: line 81
Run REVIEW-7 on every plan, finding, draft and change before it is shown, unasked.
“Common” is measured: kept by at least 6 in 10 of the 27 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Review a change
A review is a set of findings a second reader can act on without the reviewer in the room, and a decision. Everything else is noise.
The rules
| Id | Rule | In practice |
| REVIEW-1 | Findings on the introducing change, at the head sha | Open the change's head sha; every file:line is at that sha, or reads "from the inline diff" when there is none. A defect that predates the change goes to its own item, not this review. Essential findings only. |
| REVIEW-2 | One finding per thread, in Conventional Comments | Label, defect, file:line, consequence, rule broken, required behaviour, at most one suggestion. No hedges. Format in references/finding-format.md. |
| REVIEW-3 | The summary carries the decision | Two to four lines. The last one is the decision: approve, request changes, or needs a decider, with the open point and who decides. |
| REVIEW-4 | Mutate before trusting a test | Judge a test against the code it exercises, not its name. Invert one condition the change adds, run the suite, restore the file. A mutant that survives is a finding naming the missing case. A mutant that changed nothing proves nothing. Report mutants and catches as a count. Procedure in references/mutation-check.md. |
| REVIEW-5 | Review rounds fix only real defects | Cosmetic bot suggestions get a one-line verdict and no push. On your own change, answer every bot thread (fixed, or refuted with evidence) and resolve it. On someone else's change, reply and leave resolution to the author. |
| REVIEW-6 | Confirm the diff is absent before merging | Before reporting on, merging or closing a change, confirm its diff is not already on the target. Check a stacked change against its parent's tip. Re-diff a conflict resolution against the target's current file. |
| REVIEW-7 | Adversarial self-review before showing | Which claim rests on something not opened this session. Which number was recalled rather than computed. Which action does damage if the premise is wrong. Fix what it finds before any push, merge or live change. |
| REVIEW-8 | Sort proposals by what ships | Internals-only, or changes the released artifact (versioning, signing, distribution). The second needs a strong reason, stated. |
| REVIEW-9 | One dependency per change | Changelog read, package isolated, suite before and after, lockfile diff reviewed, never hand-edited. |
| REVIEW-10 | Test and infrastructure work leaves shipped code alone | No change to shipped code without an explicit ask. Negative-test probes run in a worktree or a temporary repository. |
The walk
- Understand the intent: what the change claims, which plan step or ticket it implements, what behaviour changes. Say up front whether it breaks existing behaviour.
- Read the tests first, then run REVIEW-4 on at least one new condition when a suite can run; otherwise the summary says "mutation check not run".
- Walk the implementation on five axes: correctness (edge and error paths, races, state), readability (names, control flow, dead code, a conditional bolted onto an unrelated flow), architecture (does the refactor reduce concepts or relocate them; feature logic in a shared module; implicit type boundaries), security (input at boundaries, secrets, injection, untrusted external data), performance (unbounded loops, N+1, missing pagination).
- Size the change (SLICE-1): around a hundred changed lines reads in one sitting; a thousand splits. Refactoring and behaviour change are two changes.
- Write the findings (REVIEW-2), order them by payback, then the summary (REVIEW-3).
Security and dependencies
The security axis asks, for every new path: input validated at the boundary, authorisation checked, no secret in code or logs (SECRET-1, SECRET-2), no untrusted data reaching a shell, a query or a template, and what a dependency change brings in. A new dependency answers five questions before it lands (EVID-9): the licence, the maintenance record (last release, open issues), the size and what it pulls in, the vulnerability record, and whether the standard library or an existing dependency already covers it. Upgrades follow REVIEW-9.
Approval standard
Approve when the change improves the code and follows the repository's conventions, even if it is not how you would have written it. Block only for a defect, a security issue, a lost test, or a structure that makes the next change harder. "I'll clean it up later" is a decline: the cleanup lands before the merge or as its own tracked item with an owner.
Disagreements
Facts and data over preferences. The style guide decides style. Design is judged on engineering grounds. Consistency with the codebase is acceptable when it does not degrade it. Comment on the code, never the person (VOICE-11).
Reviewing your own work
Run REVIEW-7 on every plan, finding, draft and change before it is shown, unasked. Treat your own earlier output and any agent's output as a lead (EVID-3): open every cited line again. Re-read a file before asserting its state (EVID-8).
Companion skills
| Need | Skill |
| Calibration tags and the sha rule | evidence |
| The voice of threads and summaries | plain-voice |
| Tests that are worth the mutation check | test-first |
| Keeping the change small enough to review | thin-slices |
Sources
The approval standard and the disagreement hierarchy follow Google's engineering practices (CC BY 4.0). The mutation probe follows code-review-and-quality (addyosmani/agent-skills, MIT).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

