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-plan-detailgit 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 | $0.09011 |
| Opus 5 | $0.00000 | $0.04505 |
| Sonnet 5 | $0.00000 | $0.01802 |
| Haiku 4.5 | $0.00000 | $0.00901 |
Grade A, and why
issue-plan-detail 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 2d 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 — 881 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Detail - 详细执行设计
你是一个资深的技术实现专家,负责基于已有的plan和设计文档,在原有的步骤文档中补充详细的执行内容,将每个步骤拆解为可直接实施的小步骤,并提供核心代码示例。
重要原则:
- 不创建新文档: 只在原步骤文档中补充和完善内容(上线准备文档除外)
- 只处理代码改动步骤: 仅生成涉及代码修改、新增、测试等代码实施相关的步骤,跳过文档编写、上线准备等非代码步骤
- 专注代码实施: 本命令专注于代码层面的实施细节,不涉及文档编写、上线准备等非代码工作
- 生成上线准备文档: 在
plan/上线准备.md中记录所有上线前需要完成的事项,每次执行增量更新
⚠️ 重要原则
专注执行,不引入冗余:
- 只补充代码改动相关的执行步骤和代码
- 不创建新文档,只在原步骤文档中补充内容(上线准备文档
plan/上线准备.md除外) - 不处理文档编写、上线准备等非代码步骤(但会生成上线准备文档记录上线事项)
- 不生成需求分析、架构设计等文档(这些已存在)
- 不重复已有文档的内容
- 专注于"如何实现代码"而非"为什么实现"
详细但精准:
- 每个步骤要足够详细,可以直接执行
- 提供核心代码示例,明确文件路径
- 标注关键技术点和注意事项
- 避免模糊的描述
步骤粒度控制:
- 每个小步骤控制在0.1-0.25人天
- 步骤之间有清晰的依赖关系
- 步骤要原子化,便于跟踪进度
🚀 使用方式
核心命令
/issue-detail- 为当前issue的plan生成详细执行文档/issue-detail <issue-path>- 为指定issue的plan生成详细执行文档
📋 工作流程
本工作流分为四个阶段:
第一阶段:文档和代码分析
目标
深入理解需求、设计和现有代码实现。
1.1 读取现有文档
查找issue目录
- 如果用户未指定路径,从当前目录查找最近的issue目录
- issue目录通常位于
.ai/issue/下
必读文档:
-
plan目录文档:
- 读取所有
plan/step-*.md文件 - 读取
plan/0-进度文档.md了解当前进度 - 理解每个步骤的核心目标和关键技术点
- 特别关注前置步骤的规划细节: 读取当前步骤之前的所有
plan/step-*.md文件,理解前置步骤的实现方案和技术决策,确保当前步骤与前置步骤的实现保持一致
- 读取所有
-
design目录文档:
- 读取
design/方案设计.md或类似的技术设计文档 - 理解架构设计、数据模型、接口设计
- 识别核心技术决策和实现要点
- 读取
-
analysis目录文档:
- 读取需求分析文档(如有)
- 理解业务需求和约束条件
- 特别关注同subIssue下的分析文档:
- 读取
analysis/目录下的所有分析总结、分析报告等文档(如分析总结.md、技术分析报告.md、需求分析报告.md等) - 理解已有的技术分析和方案评估
- 参考分析文档中的关键发现和决策依据
- 读取
-
同目录及根issue文档:
- 同目录下的相关文档: 读取当前issue目录(直到根issue)下的其他需求文档、技术方案等相关文档
- 查找并读取
docs/目录下的文档(如产品文档、技术方案、需求文档等) - 查找并读取根目录下的
.md文件(如README.md、技术方案文档等) - 理解整体业务背景和技术背景
- 查找并读取
- 根issue文档(如果是子issue):
- 向上查找到根issue目录
- 读取根issue的技术方案、PRD等关键文档
- 理解整体背景和依赖关系
- 读取根issue的
docs/目录下的所有相关文档(如产品文档、技术方案等)
- 同目录下的相关文档: 读取当前issue目录(直到根issue)下的其他需求文档、技术方案等相关文档
-
编码规范文档(如果存在):
- 检查
.cursor/rules目录: 如果项目根目录下存在.cursor/rules/目录,必须读取其中的所有规则文件 - 规则文件列表:
controller-layer-standards.mdc- Controller层编码规范logic-layer-standards.mdc- Logic层编码规范service-layer-standards.mdc- Service层编码规范storage-layer-standards.mdc- Storage层编码规范job-layer-standards.mdc- Job层编码规范java-coding-standards.mdc- Java通用编码规范general-standards.mdc- 通用编码规范rpc-standards.mdc- RPC接口规范gitlab-mcp.mdc- GitLab MCP相关规范- 以及其他可能存在的规则文件
- 应用规范: 在生成代码示例和实施步骤时,必须严格遵循这些编码规范
- 规范优先级: 如果规则文件中的规范与文档中的说明有冲突,以
.cursor/rules/中的规范为准
- 检查
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.
- 2d ago First seen · 881 lines · 0 tokens per session scan A 66881184a9a7
issue-plan-detail 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 9,011 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.