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 5.5 | $0.00046 | $0.00926 |
| Sonnet 5.5 | $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 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 — 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.
- 2mo 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 7d ago), licensed MIT. It adds 114 tokens to every session and 2,316 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
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"…
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…
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…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…