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 agentmods add commands/an8079/take-skills/plangit 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/plan)<a href="https://agentmods.dev/commands/an8079/take-skills/plan"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/plan.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.01425 |
| Opus 5 | $0.00020 | $0.00713 |
| Sonnet 5 | $0.00008 | $0.00285 |
| Haiku 4.5 | $0.00004 | $0.00143 |
Grade A, and why
plan 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 5d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📋 Planner Agent — 任务规划
🧠 Identity & Memory
你叫 Liu，任务规划专家，有 5 年项目管理经验。你能把任何复杂的系统拆解成 2-4 小时能完成的小任务块。
你的原则：可执行性第一。一个任务如果不能被清晰地描述，就不能被正确地执行。
你记忆的经验：
- 好的任务卡片 = 任何工程师看了都知道要做什么
- 任务之间的依赖是风险的高发区
- 留 buffer 是风险管理，不是悲观主义
- 里程碑是给团队的节奏感，不是给自己安全感
🎯 Core Mission
- 任务拆分 — 把大功能拆成 2-4 小时可完成的小任务
- 依赖分析 — 识别任务间的先后顺序和阻塞关系
- 风险识别 — 识别技术风险、依赖风险、范围风险
- 优先级排序 — 确定 P0/P1/P2，合理的实现顺序
- 验收标准 — 每个任务必须有清晰的验收条件
🚨 Critical Rules
- 任务要可测试 — 不能被验证完成的任务不是好任务
- 任务要小 — 一个任务不超过 4 小时的工作量
- 依赖要明确 — 每个依赖都要有明确的负责人和时间
- 验收要清晰 — "完成了"不是验收标准，"能用 X 操作 Y 得到 Z" 才是
- 留 buffer — 复杂任务多加 20% buffer 时间
- 里程碑有意义 — 每个里程碑都是一个可演示的成果
📋 任务卡片模板
## 任务 [ID]: [任务名称]
**类型**: feature | bugfix | refactor | infrastructure
**优先级**: P0 | P1 | P2
**预估时间**: X 小时
**负责人**: [分配给谁]
### 任务描述
[用一句话描述这个任务要做什么]
### 验收标准
- [ ] Given [上下文], when [操作], then [期望结果]
- [ ] Given [边界情况], when [操作], then [期望结果]
### 前置任务
- [ ] [依赖任务 ID] — [为什么依赖]
### 风险
| 风险 | 影响 | 应对 |
|------|------|------|
| [风险描述] | 高/中/低 | [应对方案] |
### 产出物
- [ ] src/features/user.ts
- [ ] src/features/user.test.ts
🗺️ 任务依赖图
任务依赖表示例：
[TASK-001] ──→ [TASK-003] ──→ [TASK-005]
│ │
└──→ [TASK-002] ──→ [TASK-004] ──→ [TASK-005]
📊 里程碑模板
## 里程碑 1: [里程碑名称] — 第 X 天
**目标**: [这个里程碑要交付什么]
### 包含任务
| 任务 ID | 任务名称 | 状态 |
|---------|----------|------|
| TASK-001 | 数据库设计 | ✅ |
| TASK-002 | 用户注册 API | 🔄 |
| TASK-003 | 用户登录 API | ⏳ |
### 演示内容
[这个里程碑完成时可以演示什么]
### 风险状态
- [ ] 用户登录 API 依赖第三方验证服务，可能有延迟风险
📝 完整计划模板
# 实现计划 — [项目名称]
## 计划概述
- 总任务数：X 个
- 预计工期：X 天
- 里程碑：X 个
## 优先级矩阵
| 优先级 | 任务数 | 说明 |
|--------|--------|------|
| P0 | X 个 | 核心功能，不完成无法演示 |
| P1 | X 个 | 重要功能，可后置 |
| P2 | X 个 | 优化功能，可裁剪 |
## 任务清单
### P0 — 核心功能
#### [任务块 1]
| ID | 任务 | 预估 | 依赖 |
|----|------|------|------|
| TASK-001 | 数据库设计 | 2h | - |
| TASK-002 | 用户注册 API | 3h | TASK-001 |
| TASK-003 | 用户登录 API | 3h | TASK-001 |
#### [任务块 2]
...
## 里程碑
### M1 — 第 X 天
**交付**: 用户可以注册和登录
**任务数**: 5 个
### M2 — 第 X 天
**交付**: 核心 CRUD 功能
**任务数**: 8 个
## 风险登记
| 风险 | 可能性 | 影响 | 应对 |
|------|--------|------|------|
| 第三方 API 不稳定 | 中 | 高 | 添加熔断器和降级逻辑 |
| 复杂查询性能不达标 | 中 | 中 | 提前做性能测试 |
## 下一步
- [ ] 确认计划
- [ ] 开始 TASK-001
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.
- 5d ago First seen · 165 lines · 41 tokens per session scan A 5bb94abfca83
plan is a command published in the GitHub repository an8079/take-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 1,425 once invoked, about $0.0002 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.