mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-05 01:50:27 +08:00
b01140ae33
- Update action-planning-agent to use gemini-wrapper for improved CLI analysis - Enhance task execution with simplified control structure and context requirements - Improve plan-deep command with input validation and clarity requirements - Add intelligent context acquisition rules to CLAUDE.md with required analysis patterns - Strengthen agent workflow coordination with TodoWrite management and context rules - Remove deprecated execution controls and streamline task execution flow System now enforces proper context gathering before implementation and provides better coordination between agents through structured TODO management. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
85 lines
2.8 KiB
Markdown
85 lines
2.8 KiB
Markdown
# Development Guidelines
|
|
|
|
## Overview
|
|
|
|
This document defines project-specific coding standards and development principles.
|
|
### CLI Tool Context Protocols
|
|
For all CLI tool usage, command syntax, and integration guidelines:
|
|
- **Gemini (Analysis)**: @~/.claude/workflows/gemini-unified.md
|
|
- **Codex (Analysis)**: @~/.claude/workflows/codex-unified.md
|
|
|
|
### Intelligent Context Acquisition
|
|
|
|
**Core Rule**: No task execution without sufficient context. Must gather project understanding before implementation.
|
|
|
|
**Context Tools**:
|
|
- **Structure**: Bash(~/.claude/scripts/get_modules_by_depth.sh) for project hierarchy
|
|
- **Module Analysis**: Bash(cd [module] && ~/.claude/scripts/gemini-wrapper -p "analyze patterns")
|
|
- **Full Analysis**:
|
|
|
|
Bash(cd [module] && ~/.claude/scripts/gemini-wrapper -p "analyze [scope] architecture")
|
|
|
|
Bash(codex --full-auto exec "analyze [scope] architecture")
|
|
|
|
**Context Requirements**:
|
|
- Identify 3+ existing similar patterns before implementation
|
|
- Map dependencies and integration points
|
|
- Understand testing framework and coding conventions
|
|
- Use Task agents for parallel context gathering when needed
|
|
|
|
## Philosophy
|
|
|
|
### Core Beliefs
|
|
|
|
- **Incremental progress over big bangs** - Small changes that compile and pass tests
|
|
- **Learning from existing code** - Study and plan before implementing
|
|
- **Pragmatic over dogmatic** - Adapt to project reality
|
|
- **Clear intent over clever code** - Be boring and obvious
|
|
|
|
### Simplicity Means
|
|
|
|
- Single responsibility per function/class
|
|
- Avoid premature abstractions
|
|
- No clever tricks - choose the boring solution
|
|
- If you need to explain it, it's too complex
|
|
|
|
## Project Integration
|
|
|
|
### Learning the Codebase
|
|
|
|
- Find 3 similar features/components
|
|
- Identify common patterns and conventions
|
|
- Use same libraries/utilities when possible
|
|
- Follow existing test patterns
|
|
|
|
### Tooling
|
|
|
|
- Use project's existing build system
|
|
- Use project's test framework
|
|
- Use project's formatter/linter settings
|
|
- Don't introduce new tools without strong justification
|
|
|
|
## Important Reminders
|
|
|
|
**NEVER**:
|
|
- Make assumptions - verify with existing code
|
|
|
|
**ALWAYS**:
|
|
- Plan complex tasks thoroughly before implementation
|
|
- Generate task decomposition for multi-module work (>3 modules or >5 subtasks)
|
|
- Track progress using TODO checklists for complex tasks
|
|
- Validate planning documents before starting development
|
|
- Commit working code incrementally
|
|
- Update plan documentation and progress tracking as you go
|
|
- Learn from existing implementations
|
|
- Stop after 3 failed attempts and reassess
|
|
|
|
|
|
#### **Content Uniqueness Rules**
|
|
|
|
- **Each layer owns its abstraction level** - no content sharing between layers
|
|
- **Reference, don't duplicate** - point to other layers, never copy content
|
|
- **Maintain perspective** - each layer sees the system at its appropriate scale
|
|
- **Avoid implementation creep** - higher layers stay architectural
|
|
|