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 adamancyzhang/claude-orchestrator-server --skill task-reviewgit clone --depth 1 https://github.com/adamancyzhang/claude-orchestrator-serverWrote 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/adamancyzhang/claude-orchestrator-server/task-review)<a href="https://agentmods.dev/skills/adamancyzhang/claude-orchestrator-server/task-review"><img src="https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/task-review/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/adamancyzhang/claude-orchestrator-server/task-review"><img src="https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/task-review.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 | $0.00114 | $0.02316 |
| Opus 5 | $0.00057 | $0.01158 |
| Sonnet 5 | $0.00023 | $0.00463 |
| Haiku 4.5 | $0.00011 | $0.00232 |
Grade A, and why
task-review 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 9d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Review
审查不是挑刺,是从设计意图的高度判断实现是否"做对了"——不是"代码写得怎么样",而是"该不该通过"。本技能与 [[task-traceability]] 协作,确保每次审查有依据、有深度、有结论、可追溯——每个判定都可追溯到具体的 Plan 意图、Build 产出和 Verify 发现。
何时触发
- Verifier 完成验证,责任链流转到 Review 阶段
- Worker 通过
claude-orchestrator claim-task认领了 review 类型的任务 - 用户说"审查一下这个 PR"、"review 一下代码"
- 蓝图中有 review 类型的任务需要开工
审查六步法
按顺序执行,每一步通过才进入下一步。
1. 认领 Review 任务并收集全链信息
# 认领审查任务
claude-orchestrator claim-task
# 获取蓝图
claude-orchestrator get-context --key plan-<目标slug>
# 获取验证报告
claude-orchestrator get-context --key verify-<目标slug>
收集审查所需的完整上下文:
- Planner 的蓝图(设计意图、验收标准、范围边界)
- Builder 的代码变更(commit diff)
- Verifier 的验证报告(问题清单、回归结果)
- Builder 的 task-traceability 记录(commit hash 链)
如果缺少任何一环的产出 → 退回要求补齐。Reviewer 不做信息不完整的审查。
2. 审查设计一致性
对照蓝图检查实际实现,回答三个核心问题:
做对了吗?(功能正确性)
- 代码变更是否实现了蓝图定义的全部功能?
- 是否有蓝图定义但未实现的部分?
- 是否有蓝图未定义但被实现了的部分(越界)?
做合适吗?(架构合规性)
- 代码结构是否符合项目现有的架构模式?
- 是否引入了新的依赖或模式变更?(如有,是否必要且有充分理由?)
- 命名、目录组织、接口设计与项目现有风格是否一致?
技术债务可控吗?
- 是否有明显的性能问题、安全问题、可维护性问题?
- 是否引入了难以测试的逻辑?
- 错误处理是否合理?
# 查看完整 diff
git show <commit-hash> --patch
# 查看变更的文件列表
git show <commit-hash> --stat
3. 审查验证报告的完整性
审查 Verifier 的工作质量:
- 验证报告是否覆盖了蓝图中所有验收标准?
- 验证方法是否独立可复现?(不是转述 Builder 的结果)
- 回归测试是否被执行且通过?
- Verifier 发现的问题是否被充分描述和分类?
如果验证报告有缺陷(漏检、方法不当)→ 标记为 Review 前置条件不满足,退回 Verifier 补充。
4. 判定问题等级
对发现的问题按严重度分级:
| 级别 | 定义 | 示例 | 处理 |
|---|---|---|---|
| P0 | 阻断:设计意图未实现,核心功能缺失或不正确 | 蓝图要求的功能完全没做、引入安全漏洞 | 退回 Builder 重做 |
| P1 | 严重:实现偏离设计意图,但不影响核心功能 | 错误处理不完整、UI 与设计不一致、性能明显下降 | 退回 Builder 修改 |
| P2 | 一般:代码质量、风格、可维护性问题 | 命名不清晰、缺少注释、测试覆盖面不足 | 建议修改,不阻断通过 |
| P3 | 建议:优化建议,不影响通过 | 更好的实现方式、可选的性能优化 | 记录,Builder 自行决定 |
5. 书写审查报告
# 审查报告
> Reviewer | YYYY-MM-DD | 审查范围:<目标名称> (P→B→V 全链)
## 审查结论:Pass / Revise
(一句话结论)
---
## 审查范围
| 环节 | 负责人 | 产出 | Commit / 文档 |
|------|--------|------|--------------|
| Plan | <Planner> | 蓝图 | plan-<slug> |
| Build | <Builder> | 代码 | `a1b2c3d` |
| Verify | <Verifier> | 验证报告 | verify-<slug> |
---
## 设计一致性审查
| 蓝图要求 | 实现情况 | 判定 |
|---------|---------|------|
| 功能 A:XXX | 已实现,见 `src/a.ts:42` | ✅ |
| 功能 B:YYY | 部分实现,缺少边界处理 | ⚠️ |
| 功能 C:ZZZ | 未实现 | ❌ |
---
## 代码质量审查
| 检查项 | 结果 |
|--------|------|
| 架构合规 | ✅ / ⚠️ / ❌ |
| 命名规范 | ✅ / ⚠️ / ❌ |
| 错误处理 | ✅ / ⚠️ / ❌ |
| 性能影响 | ✅ / ⚠️ / ❌ |
| 安全问题 | ✅ / ⚠️ / ❌ |
---
## 验证报告审查
| 检查项 | 结果 |
|--------|------|
| 验收标准覆盖 | 3/3 ✅ |
| 验证方法独立 | ✅ |
| 回归测试通过 | ✅ (42/42) |
| Verifier 问题充分描述 | ✅ |
---
## 问题清单
| # | 级别 | 描述 | 位置 | 责任人 |
|---|------|------|------|--------|
| 1 | P1 | 缺少错误重试逻辑 | `src/auth.ts:L42` | @Builder |
| 2 | P2 | 变量名 `tmp` 不够清晰 | `src/utils.ts:L18` | @Builder |
---
## 审查建议
(对 Builder/Planner/Verifier 的非强制性建议)
---
*Reviewer — YYYY-MM-DD*
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.
- 9d ago First seen · 221 lines · 114 tokens per session scan A 4893e6816dd1
task-review is a skill published in the GitHub repository adamancyzhang/claude-orchestrator-server (2 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 2,316 once invoked, about $0.0006 per session on Opus 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
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…