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/qinye6/pi-ccg/initgit clone --depth 1 https://github.com/qinye6/pi-ccgWhat 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 | $0.00020 | $0.00772 |
| Opus 5 | $0.00010 | $0.00386 |
| Sonnet 5 | $0.00004 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to init — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Init - 初始化项目 AI 上下文
以「根级简明 + 模块级详尽」策略生成项目 AI 上下文文档。
使用方法
/init <项目摘要或名称>
上下文
- 项目摘要：$ARGUMENTS
- 生成/更新根级与模块级
CLAUDE.md - 自动生成 Mermaid 结构图和导航面包屑
你的角色
你是协调者，负责调用子智能体完成项目扫描与文档生成。
执行工作流
⚠️ 必须按以下步骤执行，使用 Task 工具调用子智能体
🕐 步骤 1：获取当前时间戳
必须首先调用 get-current-datetime 子智能体：
Task({
subagent_type: "get-current-datetime",
prompt: "获取当前日期时间，用于文档时间戳",
description: "获取当前时间"
})
等待返回时间戳后，保存为 $TIMESTAMP 供后续使用。
🏗️ 步骤 2：调用初始化架构师
使用 init-architect 子智能体执行完整扫描：
Task({
subagent_type: "init-architect",
prompt: "扫描项目并生成 CLAUDE.md 文档。\n\n项目摘要：$ARGUMENTS\n当前时间戳：$TIMESTAMP\n工作目录：{{WORKDIR}}\n\n请执行：\n1. 阶段 A：全仓清点（文件统计、模块识别）\n2. 阶段 B：模块优先扫描（入口、接口、依赖、测试）\n3. 阶段 C：深度补捞（按需）\n4. 阶段 D：生成文档（根级 + 模块级 CLAUDE.md）\n\n输出覆盖率报告与推荐下一步。",
description: "初始化项目文档"
})
📊 步骤 3：汇总结果
子智能体完成后，向用户展示：
## 初始化结果摘要
### 根级文档
- 状态：[创建/更新]
- 主要栏目：<列表>
### 模块识别
- 识别模块数：X
- 模块列表：
1. <模块路径>
2. ...
### 覆盖率
- 已扫描文件：X / Y
- 覆盖模块：X%
- 跳过原因：<如有>
### 生成内容
- ✅ Mermaid 结构图
- ✅ N 个模块导航面包屑
### 推荐下一步
- [ ] 补扫：<路径>
安全边界
- 只读/写文档 – 不改源代码
- 忽略生成物 – 跳过
node_modules、dist、二进制文件 - 增量更新 – 重复运行时做断点续扫
关键规则
- 必须使用 Task 工具调用子智能体，不要自己执行扫描逻辑
- 先调用
get-current-datetime获取时间戳 - 再调用
init-architect执行完整扫描 - 结果在主对话打印摘要，全文由子智能体写入仓库
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 · 101 lines · 20 tokens per session scan A 30c04306980e
init is a command published in the GitHub repository qinye6/pi-ccg (10 stars, last pushed 8d ago), licensed MIT. It adds 20 tokens to every session and 772 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to init, differing in 0 lines, and is treated as a copy.
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.