Review a finished change against its plan. Spawns 1 reviewer subagent, reports ship/rework with severity-tagged findings. Use AFTER /code-build.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Skill: /code-review
ORCHESTRATOR. One reviewer subagent. Read-only — the reviewer does not fix.
## Invocation
`/code-review <slug>`
## Steps
1. **Gather**: plan `swarm-report/<slug>-plan.md` + build report `swarm-report/<slug>-build.md`
+ the diff (`git diff` for staged + unstaged, or vs the branch point).
2. **Spawn 1 reviewer** (`Task`, `general-purpose`). Prompt:
> Answer TERSE. Read `.claude/agents/code-reviewer.md` and follow it exactly.
> Plan: swarm-report/<slug>-plan.md
> Diff below:
> <paste git diff here>
Paste the diff INTO the prompt — the reviewer must not re-read the whole repo.
3. **Report** the reviewer's verdict + findings verbatim.
4. If `verdict: rework` — the findings ARE the input to a `/code-build <slug>` retry. Do not
auto-fix here; hand them back and let the user decide.
The line at the top of this page pins the label git:20261017.66ad76d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
The registry has recorded 4 versions of this file, between Aug 8, 2026 and Oct 17, 2026, about one every 23 days. Its first recorded version is graded C and its latest A.
GET https://markdownregistry.com/api/v1/artifacts/art_3hvio3ql6a6hhwgx
GET https://markdownregistry.com/api/v1/resolve?ref=alexeyshishin/as-skill/code-review
GET https://markdownregistry.com/api/v1/blob/24060fa766f8099b821889b4552d1fb241eb91652bc1b2a1cd6bf58516b3f636
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
alexeyshishin/as-skill · domains/code/skills/code-build/SKILL.md · Implement an already-approved plan from swarm-report/<slug>-plan.md. Routes each task to the executing agent that owns…
alexeyshishin/as-skill · domains/code/skills/code-debug/SKILL.md · Find the root cause of a bug or failing test. Spawns 1 debugger subagent that reproduces, ladders hypotheses, isolates…
alexeyshishin/as-skill · domains/code/skills/code-init/SKILL.md · Generate a project CLAUDE.md for Claude Code — detects build/test/lint commands and the directory layout, then writes a…
alexeyshishin/as-skill · domains/code/skills/code-plan/SKILL.md · Design a feature before writing code. Spawns planner + skeptic subagents that read the Memory Bank, argue, and write a…
alexeyshishin/as-skill · domains/content/skills/content-article-draft/SKILL.md · Turns an idea, a series of notes, or raw material into an article draft (Habr / Medium / personal blog) — with a TL;DR…
alexeyshishin/as-skill · domains/content/skills/content-documentation/SKILL.md · Structures a technical tutorial — prerequisites, a "after reading this you'll be able to do X" goal, numbered steps…
alexeyshishin/as-skill · domains/content/skills/content-factory/SKILL.md · A content factory — turns a single source into a full content package in one pass. Takes as input a finished article, a…
alexeyshishin/as-skill · domains/content/skills/content-humanizer/SKILL.md · A skill for humanizing Russian-language text. Removes signs of AI generation, makes the text feel alive. ALWAYS use…
alexeyshishin/as-skill · domains/content/skills/content-tg-post/SKILL.md · Turns an idea, a note, or raw text into a ready-to-post Telegram channel post — tight, thesis-first, in the author's…
alexeyshishin/as-skill · domains/core/skills/caveman/SKILL.md · Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full…
alexeyshishin/as-skill · domains/core/skills/memory-bank-defrag/SKILL.md · Defragment and re-actualize a project memory bank (the .assistant/ knowledge base + the project's auto-memory). Reads…
kyegomez/swarms · examples/single_agent/capabilities/skills/multiple_skill_dirs/team_skills/code-review/SKILL.md · Review Python code for bugs, missing tests and security issues using the team's shared standards
basicmachines-co/basic-memory · .agents/skills/code-review/SKILL.md · Use when reviewing Basic Machines code for house style, architecture risk, pre-merge hardening, or whether a change…
nteract/semiotic · .github/skills/code-review/SKILL.md · Review Semiotic pull requests for behavioral bugs, regressions, contract drift, and missing evidence. Use for GitHub…
cbrock84/headcount · plugins/technology/skills/code-review/SKILL.md · Conducts and responds to code review — reviewing a change for correctness, design, and risk, and evaluating review…
