Agent skill

Code Review Team

by revfactory in revfactory/harness-engineering-with-cc

PR diff에 대해 정적분석·설계·보안 3 리뷰어 + 리팩토러 4인 팀을 운영한다. An agent skill from revfactory/harness-engineering-with-cc.

Apache-2.0Auto-check passedDevelopment

Install Code Review Team

skills CLI
$ npx skills add revfactory/harness-engineering-with-cc --skill code-review-team -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install revfactory/harness-engineering-with-cc code-review-team --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/revfactory/harness-engineering-with-cc.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ex-11-06-jwt-pr-bugs/.claude/skills/code-review-team .claude/skills/code-review-team && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
code-review-team
GitHub stars
112
Token cost
~1.1k tokens
SKILL.md length
165 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
Apache-2.0

At a glance

PR diff에 대해 정적분석·설계·보안 3 리뷰어 + 리팩토러 4인 팀을 운영한다. An agent skill from revfactory/harness-engineering-with-cc.

  • Tasks that involve Code review
  • SKILL.md covers 사용 시점, 6 Phase 워크플로 (의사코드), 도구 분류 (책 본문 메모) and 주의
  • Calls gh and git

What it does

Code Review Team is an agent skill from revfactory/harness-engineering-with-cc. PR diff에 대해 정적분석·설계·보안 3 리뷰어 + 리팩토러 4인 팀을 운영한다. 트리거 - "코드 리뷰", "PR 리뷰", "리뷰 재실행", "다시 실행", "리뷰 보고서".

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Code review. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Code review

Example prompts

  • “/code-review-team”

Requirements

  • Pre-approved tools (allowed-tools): TeamCreate, AgentTool, TaskCreate, SendMessage, TeamDelete, Read, Write, Bash(gh pr diff, gh pr comment)

What it can do on your machine

Read from SKILL.md and the folder at commit d81b72b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • TeamCreate
    • AgentTool
    • TaskCreate
    • SendMessage
    • TeamDelete
    • Read
    • Write
    • Bash(gh pr diff
    • gh pr comment)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Code Review Team loads about 1.1k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 165 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from revfactory/harness-engineering-with-cc at commit d81b72b, republished under its Apache-2.0 licence (© revfactory). 165 words, ~1,055 tokens.

Download SKILL.mdSave it as .claude/skills/code-review-team/SKILL.md (or your agent's skills folder).
name
code-review-team
description
PR diff에 대해 정적분석·설계·보안 3 리뷰어 + 리팩토러 4인 팀을 운영한다. 트리거 - "코드 리뷰", "PR 리뷰", "리뷰 재실행", "다시 실행", "리뷰 보고서".
allowed-tools
TeamCreate, AgentTool, TaskCreate, SendMessage, TeamDelete, Read, Write, Bash(gh pr diff, gh pr comment)

code-review-team

4인 리뷰어 팀 오케스트레이터. 리더는 텍스트를 쓰지 않는다 — 워커 4인이 모든 보고서를 생산한다.

사용 시점

  • PR 번호가 주어지고 코드 리뷰를 요청받았을 때
  • "리뷰 재실행", "다시 실행" 같이 동일 PR을 같은 팀으로 재돌릴 때
  • 사용자가 "코드 리뷰 팀 만들어줘" 같이 책 11장 팀을 직접 지칭할 때

6 Phase 워크플로 (의사코드)

공식 도구: TeamCreate, AgentTool, TaskCreate, SendMessage, TeamDelete. 의사 함수 (실 구현 필요): parseDiff, waitForTeamCompletion, mergeReports, $ (셸 실행 헬퍼).

typescript
async function codeReviewTeam(prNumber: number) {
  // ──────────────────────────────────────────────
  // Phase 0 — 입력 수집
  // ──────────────────────────────────────────────
  const diff = await $(`gh pr diff ${prNumber}`);  // 의사: $
  await Write(`_workspace/input/pr-${prNumber}.diff`, diff);
  const parsed = parseDiff(diff);                  // 의사: parseDiff

  // ──────────────────────────────────────────────
  // Phase 1 — TeamCreate + AgentTool × 4 (worktree 격리)
  // ──────────────────────────────────────────────
  const team = await TeamCreate({
    name: "code-review",
    description: "PR diff를 4개 렌즈로 리뷰한다"
  });

  const roleMap = [
    "static-analyzer",
    "design-reviewer",
    "security-auditor",
    "refactorer"
  ];
  for (const role of roleMap) {
    await AgentTool({
      team: team.id,
      agent: role,
      isolation: "worktree"
    });
  }

  // ──────────────────────────────────────────────
  // Phase 2 — TaskCreate × 4 (for-루프)
  // ──────────────────────────────────────────────
  // 책 주의: 단건 호출은 TaskCreate 1회씩이지만, 의사 표기로는 배열 표기로도 자주 그려진다.
  // 실제로는 for-루프로 4회 호출.
  const taskSpecs = [
    { agent: "static-analyzer",  name: "정적 분석",  output: "_workspace/review/01_static.md"   },
    { agent: "design-reviewer",  name: "설계 검토",  output: "_workspace/review/02_design.md"   },
    { agent: "security-auditor", name: "보안 감사",  output: "_workspace/review/03_security.md" },
    { agent: "refactorer",       name: "리팩토링",   output: "_workspace/review/04_refactor.md",
      depends_on: ["정적 분석", "설계 검토", "보안 감사"] }
  ];
  for (const t of taskSpecs) {
    await TaskCreate({
      team: team.id,
      agent: t.agent,
      name: t.name,
      input: `_workspace/input/pr-${prNumber}.diff`,
      output: t.output,
      depends_on: t.depends_on
    });
  }

  // ──────────────────────────────────────────────
  // Phase 3 — 팬아웃 (리뷰어 3인 병렬). 동료 SendMessage는 리더 미경유.
  // ──────────────────────────────────────────────
  await waitForTeamCompletion(team.id, { tasks: ["정적 분석", "설계 검토", "보안 감사"] });
  // 워커 간 SendMessage는 워커 정의(.md)의 팀 통신 프로토콜에 따라 자율 호출.

  // ──────────────────────────────────────────────
  // Phase 4 — 생성-검증 루프 (최대 3회)
  // ──────────────────────────────────────────────
  // refactorer는 depends_on 대기 후 자동 시작. 본인이 생성·검증을 내부에서 3회 상한으로 진행.
  await waitForTeamCompletion(team.id, { tasks: ["리팩토링"] });

  // ──────────────────────────────────────────────
  // Phase 5 — 통합 · 게시 · 정리
  // ──────────────────────────────────────────────
  const reports = [
    Read("_workspace/review/01_static.md"),
    Read("_workspace/review/02_design.md"),
    Read("_workspace/review/03_security.md"),
    Read("_workspace/review/04_refactor.md")
  ];
  const merged = mergeReports(reports, { priority: ["P0", "P1", "P2"] });
  await Write("_workspace/review_report.md", merged);

  await $(`gh pr comment ${prNumber} -F _workspace/review_report.md`);
  await TeamDelete(team.id);  // workspace 보존
}

도구 분류 (책 본문 메모)

공식 5종 (실제 호출 가능):

  • TeamCreate
  • AgentTool
  • TaskCreate
  • SendMessage (워커 정의에서 직접 호출)
  • TeamDelete

의사 함수 4종 (구현자가 직접 만들어야 함):

  • parseDiff(diff) — diff 텍스트를 파일·라인 메타로
  • waitForTeamCompletion(teamId, opts) — 작업 완료 대기
  • mergeReports(reports, opts) — 4 보고서를 우선순위 정렬해 통합
  • $(cmd) — Bash 실행 헬퍼

주의

  • 리더 무발화: 본 스킬은 호출만 한다. 리뷰 본문 텍스트는 워커 4인이 생산.
  • 자동 커밋 금지: 본 스킬은 gh pr comment까지만. git commit·gh pr merge는 호출하지 않는다.
  • workspace 보존: TeamDelete 후에도 _workspace/ 디렉토리는 남는다. 사람이 재검토할 수 있게.
  • 재실행 트리거: "리뷰 재실행" 키워드로 동일 prNumber 재돌리기 가능 (이전 결과 덮어쓰기).

© revfactory, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in ex-11-06-jwt-pr-bugs/.claude/skills/code-review-team of revfactory/harness-engineering-with-cc.

Open the folder on GitHubat commit d81b72b

Compare with similar skills

Code Review Team next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Code Review Team compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Review Team this skillrevfactory/harness-engineering-with-cc112—~1.1kAutomated safety check: PassApache-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow156k—~3.5kAutomated safety check: NotesMIT
Understand Diff AnalysisEgonex-AI/Understand-Anything85k1 repos~1.4kAutomated safety check: PassMIT
Mole Bug Patternstw93/Mole69k—~2kAutomated safety check: PassGPL-3.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    156k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check: notes
  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    85k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    69k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed

More from revfactory/harness-engineering-with-cc

  • PR Review Orchestrator

    revfactory/harness-engineering-with-cc

    PR·diff·변경 파일 목록을 받아 정적 분석, 보안 검토, 테스트 영향 검토를 병렬로 수행하고 하나의 리뷰 리포트로 통합한다.

    112 GitHub stars~795 tokensUpdated 4 mo ago
    Auto-check: notes
  • Tip Collect

    revfactory/harness-engineering-with-cc

    Claude Code 사용 팁의 소재를 신뢰 가능한 소스에서 모으는 절차. An agent skill from revfactory/harness-engineering-with-cc.

    112 GitHub stars~204 tokensUpdated 4 mo ago
    Auto-check passed
  • Tip Format

    revfactory/harness-engineering-with-cc

    tips/ 하위 팁 문서의 표준 포맷과 프론트매터 규약. An agent skill from revfactory/harness-engineering-with-cc.

    112 GitHub stars~153 tokensUpdated 4 mo ago
    Auto-check passed
  • Tip Publish

    revfactory/harness-engineering-with-cc

    작성된 팁 문서를 tips/에 저장하고 tips/README.md 인덱스를 갱신하는 발행 절차. An agent skill from revfactory/harness-engineering-with-cc.

    112 GitHub stars~144 tokensUpdated 4 mo ago
    Auto-check passed
  • Commit Message

    revfactory/harness-engineering-with-cc

    스테이지된 변경을 바탕으로 Conventional Commits 형식의 커밋 메시지를 2인 팀(author·reviewer)으로 생성.

    112 GitHub stars~222 tokensUpdated 4 mo ago
    Auto-check: notes
  • Mini Multi Mode

    revfactory/harness-engineering-with-cc

    다중 모드 오케스트레이터 — README 작성/변경로그 생성/PR 본문 작성. An agent skill from revfactory/harness-engineering-with-cc.

    112 GitHub stars~143 tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Code Review Team

What does Code Review Team do?

PR diff에 대해 정적분석·설계·보안 3 리뷰어 + 리팩토러 4인 팀을 운영한다. An agent skill from revfactory/harness-engineering-with-cc. Code Review Team is an agent skill from revfactory/harness-engineering-with-cc. PR diff에 대해 정적분석·설계·보안 3 리뷰어 + 리팩토러 4인 팀을 운영한다.

When should I use Code Review Team?

Code Review Team fits situations like: tasks that involve Code review.

How do I install Code Review Team in Claude Code?

Run `npx skills add revfactory/harness-engineering-with-cc --skill code-review-team -a claude-code`. Or copy the skill folder (ex-11-06-jwt-pr-bugs/.claude/skills/code-review-team in revfactory/harness-engineering-with-cc) into .claude/skills/code-review-team in your project. Claude Code loads it when a task matches its description.

How do I install Code Review Team in Codex?

Run `npx skills add revfactory/harness-engineering-with-cc --skill code-review-team -a codex`. Or copy the skill folder (ex-11-06-jwt-pr-bugs/.claude/skills/code-review-team in revfactory/harness-engineering-with-cc) into .agents/skills/code-review-team in your project. Codex loads it when a task matches its description.

Can I use Code Review Team in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add revfactory/harness-engineering-with-cc --skill code-review-team -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-review-team, .gemini/skills/code-review-team, .github/skills/code-review-team and .opencode/skills/code-review-team in your project.

What does Code Review Team need to run?

Going by SKILL.md and its folder, Code Review Team needs the command-line tools its instructions call (gh and git). Its frontmatter pre-approves these tools: TeamCreate, AgentTool, TaskCreate, SendMessage, TeamDelete, Read, Write, Bash(gh pr diff, gh pr comment).

Does Code Review Team access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Code Review Team safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Code Review Team use?

Code Review Team is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Review Team use?

About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Code Review Team?

Skills that share tags, products or a category with Code Review Team: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 156k stars) and Understand Diff Analysis (Egonex-AI/Understand-Anything, 85k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Review Team?

revfactory (a GitHub user) maintains it in revfactory/harness-engineering-with-cc, which has 112 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on May 26, 2026.

Source: revfactory/harness-engineering-with-cc on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.