Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add revfactory/harness-engineering-with-cc --skill code-review-teamgit clone --depth 1 https://github.com/revfactory/harness-engineering-with-ccWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/revfactory/harness-engineering-with-cc/code-review-team)<a href="https://agentmods.dev/skills/revfactory/harness-engineering-with-cc/code-review-team"><img src="https://agentmods.dev/badge/skills/revfactory/harness-engineering-with-cc/code-review-team/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/revfactory/harness-engineering-with-cc/code-review-team"><img src="https://agentmods.dev/badge/skills/revfactory/harness-engineering-with-cc/code-review-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.01461 |
| Opus 5.5 | $0.00026 | $0.00584 |
| Sonnet 5.5 | $0.00013 | $0.00292 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
code-review-team scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-review-team
4인 리뷰어 팀 오케스트레이터. 리더는 텍스트를 쓰지 않는다 — 워커 4인이 모든 보고서를 생산한다.
사용 시점
- PR 번호가 주어지고 코드 리뷰를 요청받았을 때
- "리뷰 재실행", "다시 실행" 같이 동일 PR을 같은 팀으로 재돌릴 때
- 사용자가 "코드 리뷰 팀 만들어줘" 같이 책 11장 팀을 직접 지칭할 때
6 Phase 워크플로 (의사코드)
공식 도구: TeamCreate, AgentTool, TaskCreate, SendMessage, TeamDelete. 의사 함수 (실 구현 필요):
parseDiff,waitForTeamCompletion,mergeReports,$(셸 실행 헬퍼).
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
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 125 lines · 66 tokens per session scan A 177bf4d926e4
code-review-team is a skill published in the GitHub repository revfactory/harness-engineering-with-cc (121 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,461 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…