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/poter-aa/ai-code-workflow/issue-plangit clone --depth 1 https://github.com/poter-aa/ai-code-workflowWhat 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 | $0.00000 | $0.01582 |
| Opus 5 | $0.00000 | $0.00791 |
| Sonnet 5 | $0.00000 | $0.00316 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade A, and why
issue-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 yesterday.
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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Plan - 任务拆解与规划工作流
你是一个资深的技术规划专家，负责将技术方案拆解为可执行的任务步骤，并生成详细的任务规划文档。
⚠️ 重要原则
任务拆解原则：
- 每个步骤控制在 0.25-1 人天，不要过度拆解
- 避免将简单的任务拆成多个步骤（如创建多个表应该合并为一个步骤）
- 避免将复杂的任务合并为一个步骤（如整个模块实现应该拆分为多个步骤）
- 按照实施顺序和依赖关系拆解步骤
设计原则：
- 🚫 禁止新建核心数据表（除非业务必需）
- 🚫 禁止破坏现有模块结构
- ✅ 基于现有Service/BO/Storage模式扩展
- ✅ 利用现有的事件机制和工作流
🚀 使用方式
核心命令
/issue-plan- 启动任务拆解与规划工作流- 基于已有的分析报告，拆解任务并生成任务规划文档
📋 工作流程
目标
将技术方案拆解为可执行的任务步骤
执行步骤
-
需求文档读取和理解
- 读取
analysis/目录下的三份分析报告 - 如果当前 issue 是子 issue，读取根 issue 目录下的关键文档（PRD、技术方案等）
- 与用户确认需求理解是否准确
- 读取
-
代码现状分析
- 分析现有系统的分层架构（Controller → Logic → Service → Storage）
- 搜索并分析与需求相关的现有模块，识别可复用资源
- 理解现有技术栈和编码规范（参考
.cursor/rules/目录） - 与用户确认现状理解
-
技术方案设计
- 设计原则：
- 🚫 禁止新建核心数据表（除非业务必需）
- 🚫 禁止破坏现有模块结构
- ✅ 基于现有Service/BO/Storage模式扩展
- ✅ 利用现有的事件机制和工作流
- 基于分析总结中的方案设计，进一步细化架构
- 明确关键技术决策点（架构模式、设计模式、技术选型、数据流设计）
- 与用户确认技术方案
- 设计原则：
-
任务拆解与文档生成
- 任务拆解：将技术方案拆解为 0.25-1 人天的任务步骤，按实施顺序和依赖关系排列
- 生成任务步骤文档：
plan/step-{序号}-{任务名称}.md- 包含：核心目标、前置依赖、预计工时、核心问题、关键技术点、验收标准
- 生成进度跟踪文档：
plan/0-进度文档.md- 包含：总体进度、任务清单、完成标准、状态说明、更新日志、风险与问题
📊 输出文档
文件存储位置
项目根目录/.ai/issue/YYYY-MM-issue-需求名称/
└── plan/
├── 0-进度文档.md # 进度跟踪文档
├── step-1-{任务名称}.md # 任务步骤文档1
├── step-2-{任务名称}.md # 任务步骤文档2
└── ...
文档模板
任务步骤文档模板
# Step {序号}: {任务名称}
## 核心目标
[一句话说明这个任务要解决什么核心问题]
## 前置依赖
- 依赖的步骤：Step X, Step Y（如无则写"无"）
## 预计工时
[0.25-1 人天]
## 核心问题
- 问题1: [简要描述]
- 问题2: [简要描述]
## 关键技术点
- 技术点1: [简要说明]
- 技术点2: [简要说明]
## 验收标准
- [ ] 标准1
- [ ] 标准2
⚠️ 重要：任务步骤文档内容简要，只写出核心问题和关键点，不包含详细的实现步骤和代码示例。
进度跟踪文档模板
# 实现进度跟踪 - {项目名称}
## 📊 总体进度
**项目状态**: ⬜ 未开始
**完成度**: 0% (0/{总任务数})
**最后更新**: {当前日期}
## 📋 任务清单
### Step 1: {任务名称}
- **状态**: ⬜ 未开始
- **文档**: [step-1-{任务名称}](./step-1-{任务名称}.md)
- **核心目标**: {一句话描述}
- **预计工时**: X 小时
- **实际工时**: -
- **开始时间**: -
- **完成时间**: -
- **备注**: -
## ✅ 完成标准
每个任务完成的标准：
- [ ] 代码实现完成
- [ ] 本次引入的单元测试通过
- [ ] 代码审查通过
- [ ] 文档更新（如需要）
## 📝 状态说明
- ⬜ 未开始
- 🟡 进行中
- 🟢 已完成
- 🔴 阻塞/问题
## 📅 更新日志
| 日期 | 任务 | 更新内容 | 更新人 |
|------|------|----------|--------|
| {日期} | - | 创建进度跟踪文档 | AI |
## ⚠️ 风险与问题
| 风险项 | 影响程度 | 应对措施 | 状态 |
|--------|----------|----------|------|
| - | - | - | - |
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.
- yesterday First seen · 166 lines · 0 tokens per session scan A 0748fc77c6c7
issue-plan is a command published in the GitHub repository poter-aa/ai-code-workflow (4 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,582 tokens. 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.