catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-10 02:24:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: Wrap all CLI commands with bash() in agents and workflows

Browse Source 
Updated all CLI command examples across agent documentation and workflow
guides to use bash() wrapper for proper tool execution:

- Modified action-planning-agent.md CLI usage standards
- Updated code-developer.md analysis CLI commands
- Enhanced conceptual-planning-agent.md execution logic
- Revised code-review-test-agent.md CLI commands
- Wrapped all gemini-wrapper calls in gemini-unified.md
- Updated all codex commands in codex-unified.md

This ensures consistent tool execution patterns across all documentation
and provides clear guidance for proper CLI tool invocation.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-09-14 00:11:04 +08:00
parent 4af6a59092
commit fc8a0e69f8
6 changed files with 101 additions and 84 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.claude/agents/action-planning-agent.md
View File

@@ -42,8 +42,8 @@ You are a pure execution agent specialized in creating actionable implementation
``` ```
**Analysis CLI Usage Standards**: **Analysis CLI Usage Standards**:
- **Gemini CLI**: Use task-specific paths: `~/.claude/scripts/gemini-wrapper -p "$(.claude/scripts/read-task-paths.sh [task-json-file]) @{CLAUDE.md}" ` - **Gemini CLI**: Use task-specific paths: `bash(~/.claude/scripts/gemini-wrapper -p "$(.claude/scripts/read-task-paths.sh [task-json-file]) @{CLAUDE.md}")`
- **Codex CLI**: Use task-specific paths: `codex --full-auto exec "$(.claude/scripts/read-task-paths.sh [task-json-file]) [prompt]"` - **Codex CLI**: Use task-specific paths: `bash(codex --full-auto exec "$(.claude/scripts/read-task-paths.sh [task-json-file]) [prompt]")`
- **Follow Guidelines**: @~/.claude/workflows/gemini-unified.md and @~/.claude/workflows/codex-unified.md - **Follow Guidelines**: @~/.claude/workflows/gemini-unified.md and @~/.claude/workflows/codex-unified.md
### Deep Analysis Execution ### Deep Analysis Execution

4
.claude/agents/code-developer.md
View File

@@ -56,8 +56,8 @@ ELIF context insufficient OR task has analysis marker:
- **Purpose**: Enables autonomous development with intelligent file discovery and code generation - **Purpose**: Enables autonomous development with intelligent file discovery and code generation
**Analysis CLI Usage Standards**: **Analysis CLI Usage Standards**:
- **Gemini CLI**: Use task-specific paths from JSON: `~/.claude/scripts/gemini-wrapper -p "$(~/.claude/scripts/read-task-paths.sh [task-json-file]) [prompt]" ` - **Gemini CLI**: Use task-specific paths from JSON: `bash(~/.claude/scripts/gemini-wrapper -p "$(~/.claude/scripts/read-task-paths.sh [task-json-file]) [prompt]")`
- **Codex CLI**: Use task-specific paths from JSON: `codex --full-auto exec "$(~/.claude/scripts/read-task-paths.sh [task-json-file]) [prompt]"` - **Codex CLI**: Use task-specific paths from JSON: `bash(codex --full-auto exec "$(~/.claude/scripts/read-task-paths.sh [task-json-file]) [prompt]")`
- **Follow Guidelines**: @~/.claude/workflows/gemini-unified.md and @~/.claude/workflows/codex-unified.md - **Follow Guidelines**: @~/.claude/workflows/gemini-unified.md and @~/.claude/workflows/codex-unified.md

4
.claude/agents/code-review-test-agent.md
View File

@@ -78,7 +78,7 @@ Use the targeted review context template:
**Gemini CLI Command**: **Gemini CLI Command**:
```bash ```bash
~/.claude/scripts/gemini-wrapper -p "$(.claude/scripts/read-task-paths.sh [task-json-file]) @{CLAUDE.md} [review-analysis-prompt]" bash(~/.claude/scripts/gemini-wrapper -p "$(.claude/scripts/read-task-paths.sh [task-json-file]) @{CLAUDE.md} [review-analysis-prompt]")
``` ```
This executes a change-specific Gemini CLI command that identifies: This executes a change-specific Gemini CLI command that identifies:
@@ -96,7 +96,7 @@ Use the autonomous development context template:
**Codex CLI Command**: **Codex CLI Command**:
```bash ```bash
codex --full-auto exec "$(.claude/scripts/read-task-paths.sh [task-json-file]) [autonomous-review-prompt]" bash(codex --full-auto exec "$(.claude/scripts/read-task-paths.sh [task-json-file]) [autonomous-review-prompt]")
``` ```
This executes autonomous Codex CLI analysis that provides: This executes autonomous Codex CLI analysis that provides:

4
.claude/agents/conceptual-planning-agent.md
View File

@@ -53,7 +53,7 @@ def handle_analysis_markers(prompt):
if "[GEMINI_CLI_REQUIRED]" in prompt: if "[GEMINI_CLI_REQUIRED]" in prompt:
for dimension in dimensions: for dimension in dimensions:
result = execute_gemini_cli( result = execute_gemini_cli(
command=f"~/.claude/scripts/gemini-wrapper -p \"$(.claude/scripts/read-task-paths.sh [task-json-file]) @{{CLAUDE.md}} {dimension}\"", command=f"bash(~/.claude/scripts/gemini-wrapper -p \"$(.claude/scripts/read-task-paths.sh [task-json-file]) @{{CLAUDE.md}} {dimension}\")",
dimension=dimension, dimension=dimension,
role_context=role, role_context=role,
topic=topic topic=topic
@@ -62,7 +62,7 @@ def handle_analysis_markers(prompt):
elif "[CODEX_CLI_REQUIRED]" in prompt: elif "[CODEX_CLI_REQUIRED]" in prompt:
result = execute_codex_cli( result = execute_codex_cli(
command=f"codex --full-auto exec \"$(.claude/scripts/read-task-paths.sh [task-json-file]) {topic}\"", command=f"bash(codex --full-auto exec \"$(.claude/scripts/read-task-paths.sh [task-json-file]) {topic}\")",
autonomous_analysis=True, autonomous_analysis=True,
role_context=role, role_context=role,
topic=topic topic=topic

94
.claude/workflows/codex-unified.md
View File

@@ -8,7 +8,7 @@ type: technical-guideline
- **Purpose**: An AI-powered CLI tool for automated codebase analysis, intelligent code generation, and autonomous development workflows. - **Purpose**: An AI-powered CLI tool for automated codebase analysis, intelligent code generation, and autonomous development workflows.
- **Key Characteristic**: **No `--all-files` flag** - requires explicit `@` pattern references for file inclusion. - **Key Characteristic**: **No `--all-files` flag** - requires explicit `@` pattern references for file inclusion.
- **Directory Analysis Rule**: When user intends to analyze specific directory (cd XXX), use: `codex --cd XXX --full-auto exec "prompt"` or `cd XXX && codex --full-auto exec "@{**/*} prompt"` - **Directory Analysis Rule**: When user intends to analyze specific directory (cd XXX), use: `bash(codex --cd XXX --full-auto exec "prompt")` or `bash(cd XXX && codex --full-auto exec "@{**/*} prompt")`
- **Default Mode**: `--full-auto exec` autonomous development mode (RECOMMENDED for all tasks). - **Default Mode**: `--full-auto exec` autonomous development mode (RECOMMENDED for all tasks).
- **Primary Triggers**: - **Primary Triggers**:
- When user needs automated code generation or refactoring. - When user needs automated code generation or refactoring.
@@ -22,16 +22,16 @@ type: technical-guideline
### ⭐ **CRITICAL: Default to `--full-auto` Mode** ### ⭐ **CRITICAL: Default to `--full-auto` Mode**
> **🎯 Golden Rule**: Always start with `codex --full-auto exec "your task description"` for maximum autonomous capabilities. This is the recommended approach for 90% of development tasks. > **🎯 Golden Rule**: Always start with `bash(codex --full-auto exec "your task description")` for maximum autonomous capabilities. This is the recommended approach for 90% of development tasks.
**Why `--full-auto` Should Be Your Default:** **Why `bash(codex --full-auto)` Should Be Your Default:**
- **🧠 Intelligent File Discovery**: Codex automatically identifies relevant files without manual `@` patterns - **🧠 Intelligent File Discovery**: Codex automatically identifies relevant files without manual `@` patterns
- **🎯 Context-Aware Execution**: Understands project structure and dependencies autonomously - **🎯 Context-Aware Execution**: Understands project structure and dependencies autonomously
- **⚡ Streamlined Workflow**: No need to specify file patterns - just describe what you want - **⚡ Streamlined Workflow**: No need to specify file patterns - just describe what you want
- **🚀 Maximum Automation**: Leverages full autonomous development capabilities - **🚀 Maximum Automation**: Leverages full autonomous development capabilities
- **📚 Smart Documentation**: Automatically includes relevant CLAUDE.md files and project context - **📚 Smart Documentation**: Automatically includes relevant CLAUDE.md files and project context
**When to Use `codex --full-auto exec` with Explicit Patterns:** **When to Use `bash(codex --full-auto exec)` with Explicit Patterns:**
- ✅ When you need precise control over which files are included - ✅ When you need precise control over which files are included
- ✅ When working with specific file patterns that require manual specification - ✅ When working with specific file patterns that require manual specification
- ✅ When debugging issues with file discovery in `--full-auto` mode - ✅ When debugging issues with file discovery in `--full-auto` mode
@@ -41,30 +41,30 @@ type: technical-guideline
- **Basic Structure** (Priority Order): - **Basic Structure** (Priority Order):
```bash ```bash
codex --full-auto exec "autonomous development task" # DEFAULT & RECOMMENDED bash(codex --full-auto exec "autonomous development task") # DEFAULT & RECOMMENDED
codex --full-auto exec "prompt with @{patterns}" # For specific control needs bash(codex --full-auto exec "prompt with @{patterns}") # For specific control needs
``` ```
- **Key Commands** (In Order of Preference): - **Key Commands** (In Order of Preference):
- `codex --full-auto exec "..."` ⭐ **PRIMARY MODE** - Full autonomous development - `bash(codex --full-auto exec "...")` ⭐ **PRIMARY MODE** - Full autonomous development
- `codex --full-auto exec "..."` - Controlled execution when you need specific patterns - `bash(codex --full-auto exec "...")` - Controlled execution when you need specific patterns
- `codex --cd /path --full-auto exec "..."` - Directory-specific autonomous development - `bash(codex --cd /path --full-auto exec "...")` - Directory-specific autonomous development
- `codex --cd /path --full-auto exec "@{patterns} ..."` - Directory-specific execution with patterns - `bash(codex --cd /path --full-auto exec "@{patterns} ...")` - Directory-specific execution with patterns
- **Template Usage** (Preferred Approaches): - **Template Usage** (Preferred Approaches):
```bash ```bash
# RECOMMENDED: Full autonomous mode (let Codex handle file discovery) # RECOMMENDED: Full autonomous mode (let Codex handle file discovery)
codex --full-auto exec "Refactor authentication system using best practices" bash(codex --full-auto exec "Refactor authentication system using best practices")
# Alternative: Direct execution with explicit patterns # Alternative: Direct execution with explicit patterns
codex --full-auto exec "@{src/**/*} @{CLAUDE.md} Refactor authentication system" bash(codex --full-auto exec "@{src/**/*} @{CLAUDE.md} Refactor authentication system")
# Advanced: Template injection with autonomous mode # Advanced: Template injection with autonomous mode
codex --full-auto exec "$(cat ~/.claude/workflows/cli-templates/prompts/development/feature.txt) bash(codex --full-auto exec "$(cat ~/.claude/workflows/cli-templates/prompts/development/feature.txt)
## Task: Authentication System Refactoring ## Task: Authentication System Refactoring
- Apply modern security patterns - Apply modern security patterns
- Improve code organization - Improve code organization
- Add comprehensive tests" - Add comprehensive tests")
``` ```
### 📂 File Pattern Rules - **CRITICAL FOR CODEX** ### 📂 File Pattern Rules - **CRITICAL FOR CODEX**
@@ -111,62 +111,62 @@ type: technical-guideline
- **Module-Specific Development** - **Module-Specific Development**
```bash ```bash
# RECOMMENDED: Full autonomous mode with directory context # RECOMMENDED: Full autonomous mode with directory context
codex --cd src/auth --full-auto exec "Refactor authentication module using latest patterns" bash(codex --cd src/auth --full-auto exec "Refactor authentication module using latest patterns")
# Alternative: Full autonomous mode with explicit task description # Alternative: Full autonomous mode with explicit task description
codex --full-auto exec "Refactor the authentication module in src/auth/ using latest security patterns" bash(codex --full-auto exec "Refactor the authentication module in src/auth/ using latest security patterns")
# Fallback: Explicit patterns when autonomous mode needs guidance # Fallback: Explicit patterns when autonomous mode needs guidance
codex --full-auto exec "@{src/auth/**/*,CLAUDE.md} Refactor authentication module using latest patterns" bash(codex --full-auto exec "@{src/auth/**/*,CLAUDE.md} Refactor authentication module using latest patterns")
# Alternative: Directory-specific execution with explicit patterns # Alternative: Directory-specific execution with explicit patterns
codex --cd src/auth --full-auto exec "@{**/*,../../CLAUDE.md} Refactor authentication module using latest patterns" bash(codex --cd src/auth --full-auto exec "@{**/*,../../CLAUDE.md} Refactor authentication module using latest patterns")
``` ```
- **Basic Development Task** - **Basic Development Task**
```bash ```bash
# RECOMMENDED: Let Codex handle everything autonomously # RECOMMENDED: Let Codex handle everything autonomously
codex --full-auto exec "Implement user authentication with JWT tokens" bash(codex --full-auto exec "Implement user authentication with JWT tokens")
# Alternative: Explicit file patterns if needed # Alternative: Explicit file patterns if needed
codex --full-auto exec "@{src/**/*,*.json,CLAUDE.md} Implement user authentication with JWT" bash(codex --full-auto exec "@{src/**/*,*.json,CLAUDE.md} Implement user authentication with JWT")
``` ```
- **Template-Enhanced Development** - **Template-Enhanced Development**
```bash ```bash
# RECOMMENDED: Autonomous mode with template guidance # RECOMMENDED: Autonomous mode with template guidance
codex --full-auto exec "$(cat ~/.claude/workflows/cli-templates/prompts/development/feature.txt) bash(codex --full-auto exec "$(cat ~/.claude/workflows/cli-templates/prompts/development/feature.txt)
## Task: User Authentication System ## Task: User Authentication System
- JWT token management - JWT token management
- Role-based access control - Role-based access control
- Password reset functionality" - Password reset functionality")
# Alternative: Explicit patterns with templates # Alternative: Explicit patterns with templates
codex --full-auto exec "@{src/**/*,CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/development/feature.txt)" bash(codex --full-auto exec "@{src/**/*,CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/development/feature.txt)")
``` ```
- **Full Auto Mode (PRIMARY RECOMMENDATION)** - **Full Auto Mode (PRIMARY RECOMMENDATION)**
```bash ```bash
# OPTIMAL: Let Codex discover files and handle everything # OPTIMAL: Let Codex discover files and handle everything
codex --full-auto exec "Create a complete todo application with React and TypeScript" bash(codex --full-auto exec "Create a complete todo application with React and TypeScript")
# Alternative: Explicit patterns if you want to control file scope # Alternative: Explicit patterns if you want to control file scope
codex --full-auto exec "@{**/*} Create a complete todo application with React and TypeScript" bash(codex --full-auto exec "@{**/*} Create a complete todo application with React and TypeScript")
``` ```
- **Debugging & Analysis** - **Debugging & Analysis**
```bash ```bash
# RECOMMENDED: Autonomous debugging mode # RECOMMENDED: Autonomous debugging mode
codex --full-auto exec "$(cat ~/.claude/workflows/cli-templates/prompts/development/debugging.txt) bash(codex --full-auto exec "$(cat ~/.claude/workflows/cli-templates/prompts/development/debugging.txt)
## Issue: Performance degradation in user dashboard ## Issue: Performance degradation in user dashboard
- Identify bottlenecks in the codebase - Identify bottlenecks in the codebase
- Propose and implement optimizations - Propose and implement optimizations
- Add performance monitoring" - Add performance monitoring")
# Alternative: Explicit patterns for controlled analysis # Alternative: Explicit patterns for controlled analysis
codex --full-auto exec "@{src/**/*,package.json,CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/development/debugging.txt)" bash(codex --full-auto exec "@{src/**/*,package.json,CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/development/debugging.txt)")
``` ```
### ⭐ Best Practices & Rules ### ⭐ Best Practices & Rules
@@ -180,10 +180,10 @@ type: technical-guideline
- **Be selective**: Use specific patterns like `@{src/**/*.ts}` for targeted analysis - **Be selective**: Use specific patterns like `@{src/**/*.ts}` for targeted analysis
**Default Automation Mode (CRITICAL GUIDANCE):** **Default Automation Mode (CRITICAL GUIDANCE):**
- **`--full-auto exec` is the PRIMARY choice**: Use for 90% of all tasks - maximizes autonomous capabilities - **`bash(codex --full-auto exec)` is the PRIMARY choice**: Use for 90% of all tasks - maximizes autonomous capabilities
- **`codex --full-auto exec` with explicit patterns only when necessary**: Reserve for cases where you need explicit file pattern control - **`bash(codex --full-auto exec)` with explicit patterns only when necessary**: Reserve for cases where you need explicit file pattern control
- **Trust the autonomous intelligence**: Codex excels at file discovery, context gathering, and architectural decisions - **Trust the autonomous intelligence**: Codex excels at file discovery, context gathering, and architectural decisions
- **Start with `--full-auto exec` always**: If it doesn't meet needs, then consider explicit patterns with `exec` mode - **Start with `bash(codex --full-auto exec)` always**: If it doesn't meet needs, then consider explicit patterns with `exec` mode
#### 📋 CLAUDE.md Loading Rules #### 📋 CLAUDE.md Loading Rules
@@ -231,38 +231,38 @@ type: technical-guideline
**Pre-Development Analysis:** **Pre-Development Analysis:**
```bash ```bash
# RECOMMENDED: Autonomous pattern analysis # RECOMMENDED: Autonomous pattern analysis
codex --full-auto exec "$(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt) bash(codex --full-auto exec "$(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)
Analyze the existing codebase patterns and conventions before implementing new features." Analyze the existing codebase patterns and conventions before implementing new features.")
# Alternative: Explicit patterns if needed # Alternative: Explicit patterns if needed
codex --full-auto exec "@{src/**/*,CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)" bash(codex --full-auto exec "@{src/**/*,CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)")
``` ```
**Feature Development:** **Feature Development:**
```bash ```bash
# RECOMMENDED: Full autonomous feature development # RECOMMENDED: Full autonomous feature development
codex --full-auto exec "$(cat ~/.claude/workflows/cli-templates/prompts/development/feature.txt) bash(codex --full-auto exec "$(cat ~/.claude/workflows/cli-templates/prompts/development/feature.txt)
## Feature: Advanced Search Functionality ## Feature: Advanced Search Functionality
- Full-text search capabilities - Full-text search capabilities
- Filter and sort options - Filter and sort options
- Performance optimization - Performance optimization
- Integration with existing UI components" - Integration with existing UI components")
# Alternative: Explicit patterns when needed # Alternative: Explicit patterns when needed
codex --full-auto exec "@{**/*,CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/development/feature.txt)" bash(codex --full-auto exec "@{**/*,CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/development/feature.txt)")
``` ```
**Quality Assurance:** **Quality Assurance:**
```bash ```bash
# RECOMMENDED: Autonomous testing and validation # RECOMMENDED: Autonomous testing and validation
codex --full-auto exec "$(cat ~/.claude/workflows/cli-templates/prompts/development/testing.txt) bash(codex --full-auto exec "$(cat ~/.claude/workflows/cli-templates/prompts/development/testing.txt)
Generate comprehensive tests and perform validation for the entire codebase." Generate comprehensive tests and perform validation for the entire codebase.")
# Alternative: Specific test scope control # Alternative: Specific test scope control
codex --full-auto exec "@{src/**/*,test/**/*,CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/development/testing.txt)" bash(codex --full-auto exec "@{src/**/*,test/**/*,CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/development/testing.txt)")
``` ```
### 🎨 Advanced Usage Patterns ### 🎨 Advanced Usage Patterns
@@ -270,25 +270,25 @@ codex --full-auto exec "@{src/**/*,test/**/*,CLAUDE.md} $(cat ~/.claude/workflow
**Multi-Phase Development (Full Autonomous Workflow):** **Multi-Phase Development (Full Autonomous Workflow):**
```bash ```bash
# Phase 1: Autonomous Analysis # Phase 1: Autonomous Analysis
codex --full-auto exec "Analyze current architecture for payment system integration" bash(codex --full-auto exec "Analyze current architecture for payment system integration")
# Phase 2: Autonomous Implementation (RECOMMENDED APPROACH) # Phase 2: Autonomous Implementation (RECOMMENDED APPROACH)
codex --full-auto exec "Implement Stripe payment integration based on the analyzed architecture" bash(codex --full-auto exec "Implement Stripe payment integration based on the analyzed architecture")
# Phase 3: Autonomous Testing # Phase 3: Autonomous Testing
codex --full-auto exec "Generate comprehensive tests for the payment system implementation" bash(codex --full-auto exec "Generate comprehensive tests for the payment system implementation")
# Alternative: Explicit control when needed # Alternative: Explicit control when needed
codex --full-auto exec "@{**/*,CLAUDE.md} Analyze current architecture for payment system integration" bash(codex --full-auto exec "@{**/*,CLAUDE.md} Analyze current architecture for payment system integration")
``` ```
**Cross-Project Learning:** **Cross-Project Learning:**
```bash ```bash
# RECOMMENDED: Autonomous cross-project pattern learning # RECOMMENDED: Autonomous cross-project pattern learning
codex --full-auto exec "Implement feature X by learning patterns from ../other-project/ and applying them to the current codebase" bash(codex --full-auto exec "Implement feature X by learning patterns from ../other-project/ and applying them to the current codebase")
# Alternative: Explicit pattern specification # Alternative: Explicit pattern specification
codex --full-auto exec "@{../other-project/src/**/*,src/**/*,CLAUDE.md} Implement feature X using patterns from other-project" bash(codex --full-auto exec "@{../other-project/src/**/*,src/**/*,CLAUDE.md} Implement feature X using patterns from other-project")
``` ```
Remember: **Codex excels at autonomous development** - `--full-auto exec` mode should be your default choice. Trust its intelligence for file discovery, context gathering, and implementation decisions. Use explicit `@` patterns with `--full-auto exec` only when you need precise control over file scope. Remember: **Codex excels at autonomous development** - `bash(codex --full-auto exec)` mode should be your default choice. Trust its intelligence for file discovery, context gathering, and implementation decisions. Use explicit `@` patterns with `bash(codex --full-auto exec)` only when you need precise control over file scope.

75
.claude/workflows/gemini-unified.md
View File

@@ -17,7 +17,11 @@ type: technical-guideline
- Architectural analysis and pattern detection. - Architectural analysis and pattern detection.
- Identification of coding standards and conventions. - Identification of coding standards and conventions.
### 🎯 Intelligent Wrapper: `gemini-wrapper` ## ⭐ **RECOMMENDED: Use `gemini-wrapper` as Primary Method**
> **🎯 Core Recommendation**: Always use `gemini-wrapper` instead of direct `gemini` commands. This intelligent wrapper handles token limits, approval modes, and error management automatically.
### 🎯 Intelligent Wrapper: `gemini-wrapper` (PRIMARY METHOD)
- **Purpose**: Smart wrapper that automatically manages `--all-files` flag and approval modes based on project analysis - **Purpose**: Smart wrapper that automatically manages `--all-files` flag and approval modes based on project analysis
- **Location**: `~/.claude/scripts/gemini-wrapper` (auto-installed) - **Location**: `~/.claude/scripts/gemini-wrapper` (auto-installed)
@@ -33,6 +37,21 @@ type: technical-guideline
- **Benefits**: Prevents token limits, optimizes approval workflow, provides error tracking - **Benefits**: Prevents token limits, optimizes approval workflow, provides error tracking
- **Setup**: Script auto-installs to `~/.claude/scripts/` location - **Setup**: Script auto-installs to `~/.claude/scripts/` location
**⚡ Quick Start Examples:**
```bash
# RECOMMENDED: Let wrapper handle everything automatically
bash(~/.claude/scripts/gemini-wrapper -p "Analyze authentication patterns")
# Analysis task - wrapper auto-detects and uses --approval-mode default
bash(~/.claude/scripts/gemini-wrapper -p "Review code quality and conventions")
# Development task - wrapper auto-detects and uses --approval-mode yolo
bash(~/.claude/scripts/gemini-wrapper -p "Implement user dashboard feature")
# Directory-specific analysis
bash(cd src/auth && ~/.claude/scripts/gemini-wrapper -p "Analyze module patterns")
```
### ⚙️ Command Syntax & Arguments ### ⚙️ Command Syntax & Arguments
- **Basic Structure**: - **Basic Structure**:
@@ -50,19 +69,19 @@ type: technical-guideline
- **Template Usage**: - **Template Usage**:
```bash ```bash
# Without template (manual prompt) # Without template (manual prompt)
gemini --all-files -p "@{src/**/*} @{CLAUDE.md} Analyze code patterns and conventions" bash(gemini --all-files -p "@{src/**/*} @{CLAUDE.md} Analyze code patterns and conventions")
# With template (recommended) # With template (recommended)
gemini --all-files -p "@{src/**/*} @{CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)" bash(gemini --all-files -p "@{src/**/*} @{CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)")
# Multi-template composition # Multi-template composition
gemini --all-files -p "@{src/**/*} @{CLAUDE.md} $(cat <<'EOF' bash(gemini --all-files -p "@{src/**/*} @{CLAUDE.md} $(cat <<'EOF'
$(cat ~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt) $(cat ~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt)
Additional Security Focus: Additional Security Focus:
$(cat ~/.claude/workflows/cli-templates/prompts/analysis/security.txt) $(cat ~/.claude/workflows/cli-templates/prompts/analysis/security.txt)
EOF EOF
)" )")
``` ```
@@ -105,54 +124,54 @@ type: technical-guideline
### 📦 Standard Command Structures ### 📦 Standard Command Structures
These are recommended command templates for common scenarios. > **⚠️ IMPORTANT**: Use `gemini-wrapper` for 90% of all tasks. Only use direct `gemini` commands when you need explicit manual control.
#### 🎯 Using Intelligent Wrapper (Recommended) #### 🎯 Using Intelligent Wrapper (PRIMARY CHOICE - 90% of tasks)
- **Automatic Token & Approval Management** - **Automatic Token & Approval Management**
```bash ```bash
# Analysis task - auto adds --approval-mode default # Analysis task - auto adds --approval-mode default
~/.claude/scripts/gemini-wrapper -p "Analyze authentication module patterns and implementation" bash(~/.claude/scripts/gemini-wrapper -p "Analyze authentication module patterns and implementation")
# Execution task - auto adds --approval-mode yolo # Execution task - auto adds --approval-mode yolo
~/.claude/scripts/gemini-wrapper -p "Implement user login feature with JWT tokens" bash(~/.claude/scripts/gemini-wrapper -p "Implement user login feature with JWT tokens")
# Navigate to specific directory with wrapper # Navigate to specific directory with wrapper
cd src/auth && ~/.claude/scripts/gemini-wrapper -p "Review authentication patterns" bash(cd src/auth && ~/.claude/scripts/gemini-wrapper -p "Review authentication patterns")
# Override token threshold if needed # Override token threshold if needed
GEMINI_TOKEN_LIMIT=500000 ~/.claude/scripts/gemini-wrapper -p "Custom threshold analysis" bash(GEMINI_TOKEN_LIMIT=500000 ~/.claude/scripts/gemini-wrapper -p "Custom threshold analysis")
# Multi-directory support with wrapper # Multi-directory support with wrapper
~/.claude/scripts/gemini-wrapper --include-directories /path/to/other/project -p "Cross-project analysis" bash(~/.claude/scripts/gemini-wrapper --include-directories /path/to/other/project -p "Cross-project analysis")
``` ```
- **Module-Specific Analysis (Quick Module Analysis)** - **Module-Specific Analysis (Quick Module Analysis)**
```bash ```bash
# Navigate to module directory for focused analysis # Navigate to module directory for focused analysis
cd src/auth && ~/.claude/scripts/gemini-wrapper -p "Analyze authentication module patterns and implementation" bash(cd src/auth && ~/.claude/scripts/gemini-wrapper -p "Analyze authentication module patterns and implementation")
# Or specify module from root directory # Or specify module from root directory
cd backend/services && ~/.claude/scripts/gemini-wrapper -p "Review service architecture and dependencies" bash(cd backend/services && ~/.claude/scripts/gemini-wrapper -p "Review service architecture and dependencies")
# Template-enhanced module analysis with wrapper # Template-enhanced module analysis with wrapper
cd frontend/components && ~/.claude/scripts/gemini-wrapper -p "$(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)" bash(cd frontend/components && ~/.claude/scripts/gemini-wrapper -p "$(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)")
``` ```
#### 📝 Direct Gemini Usage (Manual Control) #### 📝 Direct Gemini Usage (Manual Control - Use Only When Needed)
- **Manual Token Management** - **Manual Token Management**
```bash ```bash
# Direct gemini usage when you want explicit control # Direct gemini usage when you want explicit control
gemini --all-files -p "Analyze authentication module patterns and implementation" bash(gemini --all-files -p "Analyze authentication module patterns and implementation")
# Fallback when wrapper suggests pattern usage # Fallback when wrapper suggests pattern usage
gemini -p "@{src/auth/**/*} @{CLAUDE.md} Analyze authentication patterns" bash(gemini -p "@{src/auth/**/*} @{CLAUDE.md} Analyze authentication patterns")
``` ```
- **Basic Structure (Manual Prompt)** - **Basic Structure (Manual Prompt)**
```bash ```bash
gemini --all-files -p "@{target_patterns} @{CLAUDE.md,**/*CLAUDE.md} bash(gemini --all-files -p "@{target_patterns} @{CLAUDE.md,**/*CLAUDE.md}
Context: [Analysis type] targeting @{target_patterns} Context: [Analysis type] targeting @{target_patterns}
Guidelines: Include CLAUDE.md standards Guidelines: Include CLAUDE.md standards
@@ -163,13 +182,13 @@ These are recommended command templates for common scenarios.
## Output: ## Output:
- File:line references - File:line references
- Code examples" - Code examples")
``` ```
- **Template-Enhanced (Recommended)** - **Template-Enhanced (Recommended)**
```bash ```bash
# Using a predefined template for consistent, high-quality analysis # Using a predefined template for consistent, high-quality analysis
gemini --all-files -p "@{target_patterns} @{CLAUDE.md,**/*CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/[category]/[template].txt) bash(gemini --all-files -p "@{target_patterns} @{CLAUDE.md,**/*CLAUDE.md} $(cat ~/.claude/workflows/cli-templates/prompts/[category]/[template].txt)
## Analysis: ## Analysis:
1. [Point 1] 1. [Point 1]
@@ -177,13 +196,12 @@ These are recommended command templates for common scenarios.
## Output: ## Output:
- File:line references - File:line references
- Code examples" - Code examples")
"
``` ```
- **Multi-Template Composition** - **Multi-Template Composition**
```bash ```bash
gemini --all-files -p "@{src/**/*} @{CLAUDE.md} bash(gemini --all-files -p "@{src/**/*} @{CLAUDE.md}
$(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt) $(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)
Additional Security Focus: Additional Security Focus:
@@ -195,8 +213,7 @@ These are recommended command templates for common scenarios.
## Output: ## Output:
- File:line references - File:line references
- Code examples" - Code examples")
"
``` ```
- **Token Limit Fallback** - **Token Limit Fallback**
@@ -204,13 +221,13 @@ These are recommended command templates for common scenarios.
# If --all-files exceeds token limits, immediately retry with targeted patterns: # If --all-files exceeds token limits, immediately retry with targeted patterns:
# Original command that failed: # Original command that failed:
gemini --all-files -p "Analyze authentication patterns" bash(gemini --all-files -p "Analyze authentication patterns")
# Fallback with specific patterns: # Fallback with specific patterns:
gemini -p "@{src/auth/**/*} @{src/middleware/**/*} @{CLAUDE.md} Analyze authentication patterns" bash(gemini -p "@{src/auth/**/*} @{src/middleware/**/*} @{CLAUDE.md} Analyze authentication patterns")
# Or focus on specific file types: # Or focus on specific file types:
gemini -p "@{**/*.ts} @{**/*.js} @{CLAUDE.md} Analyze authentication patterns" bash(gemini -p "@{**/*.ts} @{**/*.js} @{CLAUDE.md} Analyze authentication patterns")
``` ```
### ⭐ Best Practices & Rules ### ⭐ Best Practices & Rules