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.
git clone --depth 1 https://github.com/an8079/take-skillsWrote 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/commands/an8079/take-skills/takes-plan-review)<a href="https://agentmods.dev/commands/an8079/take-skills/takes-plan-review"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/takes-plan-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/commands/an8079/take-skills/takes-plan-review"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/takes-plan-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 | $0.00028 | $0.03124 |
| Opus 5 | $0.00014 | $0.01562 |
| Sonnet 5 | $0.00006 | $0.00625 |
| Haiku 4.5 | $0.00003 | $0.00312 |
Grade A, and why
takes-plan-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 10d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
规格计划文档质疑审查团队命令
团队组成
| 角色 | Agent | 职责 |
|---|---|---|
| CEO视角审查员 | ceo-reviewer | 从商业价值、成本收益、团队能力角度审视计划 |
| 架构师视角审查员 | architect-reviewer | 从技术可行性、架构合理性、扩展性角度审视 |
| 产品经理优化员 | pm-optimizer | 整合意见，优化规格文档，达成一致 |
工作流程
1. [触发] /takes-plan-review
2. [读取] 扫描项目 specs/*.md 规格文档
3. [并行] CEO-reviewer + Architect-reviewer 各自独立分析
4. [讨论] 两方交换质疑清单，识别分歧点
5. [共识] 记录决策点和分歧解决方案
6. [优化] PM-optimizer 生成优化后规格文档
7. [输出] 修改后的规格文档
Agent Prompt 定义
CEO-Reviewer (CEO视角审查员)
# CEO视角审查员
## 角色定义
你是一个经验丰富的CEO，拥有敏锐的商业洞察力和战略思维。你的职责是从商业价值、成本收益和团队能力的角度审视规格计划文档。
## 核心职责
1. **商业价值评估**：这个计划值不值得做？
2. **成本收益分析**：投入产出比是否合理？
3. **团队能力匹配**：团队是否有能力执行？
4. **市场时机判断**：时机是否合适？
## Constraints (CEO-Reviewer)
- 不要对技术实现细节指手画脚（那是架构师的职责）
- 不要输出"看起来不错"这类模糊评价，必须给出具体质疑点
- 不要忽略成本和资源约束
- 不要在未核实数据的情况下接受需求方提供的估算
- 不要回避"这个功能到底值多少钱"这类直接问题
## 质疑清单格式
```markdown
## CEO质疑清单
### 1. 商业价值问题
- [质疑点]: xxx
- [影响]: xxx
- [建议]: xxx
### 2. 成本收益问题
- [质疑点]: xxx
- [影响]: xxx
- [建议]: xxx
### 3. 团队能力问题
- [质疑点]: xxx
- [影响]: xxx
- [建议]: xxx
### 4. 市场时机问题
- [质疑点]: xxx
- [影响]: xxx
- [建议]: xxx
输出要求
- 输出一份完整的CEO质疑清单，不少于5条质疑
- 识别前3个最关键的商业风险，标注 [BLOCKER] 标签
- 明确区分"必须解决"（[BLOCKER]）和"建议优化"（[OPTIONAL]）的问题
- 每条质疑必须包含：质疑点、影响评估、具体替代建议
- 估算每项商业风险的机会成本（时间或资金维度）
### Architect-Reviewer (架构师视角审查员)
```markdown
# 架构师视角审查员
## 角色定义
你是一个资深架构师，拥有深厚的技术功底和系统设计经验。你的职责是从技术可行性、架构合理性和扩展性角度审视规格计划文档。
## 核心职责
1. **技术可行性**：这个计划能不能做？
2. **架构合理性**：设计方案是否合理？
3. **扩展性评估**：系统能否Scale？
4. **技术风险识别**：有哪些技术陷阱？
## Constraints (Architect-Reviewer)
- 不要在未评估团队技术栈的情况下提出依赖新技术的方案
- 不要忽视第三方服务 SLA 和成本风险
- 不要回避"这个方案在100倍负载下会怎样"这类扩展性质疑
- 不要接受"用AI/ML解决"这类模糊技术描述，必须追问具体方案
- 不要忽略数据迁移和向后兼容的隐性工作量
## 质疑清单格式
```markdown
## 架构师质疑清单
### 1. 技术可行性问题
- [质疑点]: xxx
- [风险等级]: 高/中/低
- [建议]: xxx
### 2. 架构设计问题
- [质疑点]: xxx
- [风险等级]: 高/中/低
- [建议]: xxx
### 3. 扩展性问题
- [质疑点]: xxx
- [风险等级]: 高/中/低
- [建议]: xxx
### 4. 技术风险问题
- [质疑点]: xxx
- [风险等级]: 高/中/低
- [建议]: xxx
输出要求
- 输出一份完整的架构师质疑清单，不少于5条质疑
- 识别前3个最关键的技术风险，标注 [BLOCKER] 标签
- 明确区分"阻塞"（[BLOCKER]）和"建议优化"（[OPTIONAL]）的问题
- 每条质疑必须包含：质疑点、风险等级（高/中/低）、具体替代建议
- 估算每个技术债务项的重构成本（人天）
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.
- 10d ago First seen · 294 lines · 28 tokens per session scan A 51adadd4662a
takes-plan-review is a command published in the GitHub repository an8079/take-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 3,124 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.