mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-13 02:41:50 +08:00
docs: Update workflow documentation and context search strategy
Updated workflow docs command and refined context search strategy guidelines. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -26,8 +26,8 @@ examples:
|
|||||||
### Planning & Task Creation Process
|
### Planning & Task Creation Process
|
||||||
The command performs structured planning and task creation:
|
The command performs structured planning and task creation:
|
||||||
|
|
||||||
**0. Pre-Planning Architecture Analysis** ⚠️ FIRST STEP
|
**0. Pre-Planning Architecture Analysis** ⚠️ MANDATORY FIRST STEP
|
||||||
- **System Structure Analysis**: Run `bash(~/.claude/scripts/get_modules_by_depth.sh)` to discover project hierarchy
|
- **System Structure Analysis**: MUST run `bash(~/.claude/scripts/get_modules_by_depth.sh)` for dynamic task decomposition
|
||||||
- **Module Boundary Identification**: Understand module organization and dependencies
|
- **Module Boundary Identification**: Understand module organization and dependencies
|
||||||
- **Architecture Pattern Recognition**: Identify architectural styles and design patterns
|
- **Architecture Pattern Recognition**: Identify architectural styles and design patterns
|
||||||
- **Foundation for documentation**: Use structure analysis to guide task decomposition
|
- **Foundation for documentation**: Use structure analysis to guide task decomposition
|
||||||
|
|||||||
@@ -11,14 +11,20 @@ type: search-guideline
|
|||||||
**rg (ripgrep)**: Fast content search with regex support
|
**rg (ripgrep)**: Fast content search with regex support
|
||||||
**find**: File/directory location by name patterns
|
**find**: File/directory location by name patterns
|
||||||
**grep**: Built-in pattern matching in files
|
**grep**: Built-in pattern matching in files
|
||||||
|
**get_modules_by_depth.sh**: Program architecture analysis and structural discovery
|
||||||
|
|
||||||
### Decision Principles
|
### Decision Principles
|
||||||
- **Use rg for content** - Fastest for searching within files
|
- **Use rg for content** - Fastest for searching within files
|
||||||
- **Use find for files** - Locate files/directories by name
|
- **Use find for files** - Locate files/directories by name
|
||||||
- **Use grep sparingly** - Only when rg unavailable
|
- **Use grep sparingly** - Only when rg unavailable
|
||||||
|
- **Use get_modules_by_depth.sh first** - MANDATORY for program architecture analysis before planning
|
||||||
|
|
||||||
### Quick Command Reference
|
### Quick Command Reference
|
||||||
```bash
|
```bash
|
||||||
|
# Program Architecture Analysis (MANDATORY FIRST)
|
||||||
|
~/.claude/scripts/get_modules_by_depth.sh # Discover program architecture
|
||||||
|
bash(~/.claude/scripts/get_modules_by_depth.sh) # Analyze structural hierarchy
|
||||||
|
|
||||||
# Content Search (rg preferred)
|
# Content Search (rg preferred)
|
||||||
rg "pattern" --type js # Search in JS files
|
rg "pattern" --type js # Search in JS files
|
||||||
rg -i "case-insensitive" # Ignore case
|
rg -i "case-insensitive" # Ignore case
|
||||||
@@ -36,6 +42,10 @@ grep -n -i "pattern" file.txt # Line numbers, case-insensitive
|
|||||||
|
|
||||||
### Workflow Integration Examples
|
### Workflow Integration Examples
|
||||||
```bash
|
```bash
|
||||||
|
# Program Architecture Analysis (MANDATORY BEFORE PLANNING)
|
||||||
|
~/.claude/scripts/get_modules_by_depth.sh # Discover program architecture
|
||||||
|
bash(~/.claude/scripts/get_modules_by_depth.sh) # Analyze structural hierarchy
|
||||||
|
|
||||||
# Search for task definitions
|
# Search for task definitions
|
||||||
rg "IMPL-\d+" .workflow/ --type json # Find task IDs
|
rg "IMPL-\d+" .workflow/ --type json # Find task IDs
|
||||||
find .workflow/ -name "*.json" -path "*/.task/*" # Locate task files
|
find .workflow/ -name "*.json" -path "*/.task/*" # Locate task files
|
||||||
|
|||||||
Reference in New Issue
Block a user