Usage
/init-project <PROJECT_SUMMARY_OR_NAME>
Objective
Initialize project AI context using a mixed strategy of "concise at root + detailed at module level":
- Generate/update
CLAUDE.md at repository root (high-level vision, architecture overview, module index, global standards).
- Generate/update local
CLAUDE.md in identified module directories (interfaces, dependencies, entry points, tests, key files, etc.).
- ✨ For improved readability, automatically generate Mermaid structure diagrams in the root
CLAUDE.md and add navigation breadcrumbs to each module CLAUDE.md.
Orchestration Instructions
Step 1: Call the get-current-datetime sub-agent to obtain the current timestamp.
Step 2: Call the init-architect sub-agent once, with input:
project_summary: $ARGUMENTScurrent_timestamp: (timestamp from step 1)
Execution Strategy (Agent adapts automatically, no user parameters needed)
- Stage A: Repository Census (Lightweight)
Quickly count files and directories, identify module roots (package.json, pyproject.toml, go.mod, apps/, packages/, services/*, etc.).
- Stage B: Module Priority Scanning (Medium)
For each module, perform targeted reading and sampling of "entry/interfaces/dependencies/tests/data models/quality tools".
- Stage C: Deep Supplementation (As Needed)
If repository is small or module scale is small, expand reading scope; if large, perform batch supplemental scanning on high-risk/high-value paths.
- Coverage Measurement and Resumability
Output "scanned files / estimated total files, covered module ratio, ignored/skipped reasons" and list "recommended next-step deep-dive sub-paths". When running
/init-project repeatedly, perform incremental updates and breakpoint resumable scanning based on previous index.
Security and Boundaries
- Only read/write documentation and indexes, do not modify source code.
- Ignore common generated artifacts and binary large files by default.
- Print "summary" in main dialog, write full content to repository.
Output Requirements
- Print "Initialization Result Summary" in main dialog, including:
- Whether root-level
CLAUDE.md was created/updated, major section overview.
- Number of identified modules and their path list.
- Generation/update status of each module's
CLAUDE.md.
- ✨ Explicitly mention "Generated Mermaid structure diagram" and "Added navigation breadcrumbs for N modules".
- Coverage and major gaps.
- If not fully read: explain "why stopped here" and list recommended next steps (e.g., "suggest priority supplemental scanning: packages/auth/src/controllers").
1---
2name: init-project
3description: Initialize project AI context, generate/update root-level and module-level CLAUDE.md indexes
4disable-model-invocation: true
5allowed-tools: Read(**), Write(CLAUDE.md, **/CLAUDE.md)
6---
7
8## Usage
9
10`/init-project <PROJECT_SUMMARY_OR_NAME>`
11
12## Objective
13
14Initialize project AI context using a mixed strategy of "concise at root + detailed at module level":
15
16- Generate/update `CLAUDE.md` at repository root (high-level vision, architecture overview, module index, global standards).
17- Generate/update local `CLAUDE.md` in identified module directories (interfaces, dependencies, entry points, tests, key files, etc.).
18- ✨ **For improved readability, automatically generate Mermaid structure diagrams in the root `CLAUDE.md` and add navigation breadcrumbs to each module `CLAUDE.md`**.
19
20## Orchestration Instructions
21
22**Step 1**: Call the `get-current-datetime` sub-agent to obtain the current timestamp.
23
24**Step 2**: Call the `init-architect` sub-agent once, with input:
25
26- `project_summary`: $ARGUMENTS
27- `current_timestamp`: (timestamp from step 1)
28
29## Execution Strategy (Agent adapts automatically, no user parameters needed)
30
31- **Stage A: Repository Census (Lightweight)**
32 Quickly count files and directories, identify module roots (package.json, pyproject.toml, go.mod, apps/_, packages/_, services/\*, etc.).
33- **Stage B: Module Priority Scanning (Medium)**
34 For each module, perform targeted reading and sampling of "entry/interfaces/dependencies/tests/data models/quality tools".
35- **Stage C: Deep Supplementation (As Needed)**
36 If repository is small or module scale is small, expand reading scope; if large, perform batch supplemental scanning on high-risk/high-value paths.
37- **Coverage Measurement and Resumability**
38 Output "scanned files / estimated total files, covered module ratio, ignored/skipped reasons" and list "recommended next-step deep-dive sub-paths". When running `/init-project` repeatedly, perform **incremental updates** and **breakpoint resumable scanning** based on previous index.
39
40## Security and Boundaries
41
42- Only read/write documentation and indexes, do not modify source code.
43- Ignore common generated artifacts and binary large files by default.
44- Print "summary" in main dialog, write full content to repository.
45
46## Output Requirements
47
48- Print "Initialization Result Summary" in main dialog, including:
49 - Whether root-level `CLAUDE.md` was created/updated, major section overview.
50 - Number of identified modules and their path list.
51 - Generation/update status of each module's `CLAUDE.md`.
52 - ✨ **Explicitly mention "Generated Mermaid structure diagram" and "Added navigation breadcrumbs for N modules"**.
53 - Coverage and major gaps.
54 - If not fully read: explain "why stopped here" and list **recommended next steps** (e.g., "suggest priority supplemental scanning: packages/auth/src/controllers").
UfoMiao