4a69c5323b
- Update README.md with correct model assignments for all agents - Sync AGENTS.md and .kilo/ files with new model IDs - Change History Miner: Gemini-3-Flash → GPT-OSS 20B - Change System Analyst: GPT-OSS 120B → Qwen3.6-Plus (Free) - Change Product Owner: Qwen3.5 122B → Qwen3.6-Plus (Free) - Change Lead Developer: DeepSeek-v3.2 → Qwen3-Coder 480B - Change The Fixer: MiniMax-m2.7 → MiniMax-m2.5 - Change SDET Engineer: Qwen3-Coder-Next → Qwen3-Coder 480B - Change Code Skeptic: GPT-OSS 120B → MiniMax-m2.5 - Change Security Auditor: GLM-4.7 → Kimi-k2.5 - Change Release Manager: Devstral-2 123B → Qwen3-Coder 480B - Change Evaluator: GPT-o3 → GPT-OSS 120B - Change Prompt Optimizer: Claude 4.5 → Qwen3.6-Plus (Free) - Add AgentArchitect agent configuration - Update commands: plan, ask, debug, code models - Add permissions configuration to commands
2.9 KiB
2.9 KiB
description, mode, model, color, permission
| description | mode | model | color | permission | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Creates detailed task plans with breakdown, estimates, and dependencies | plan | openrouter/qwen/qwen3-coder:free | #3B82F6 |
|
Plan Command
Generates detailed implementation plans with task breakdown, complexity estimates, and dependency analysis.
Workflow
Step 1: Analyze Requirements
- Parse the user's request into clear objectives
- Identify functional requirements
- Identify non-functional requirements (performance, security, scalability)
- Clarify ambiguous points with follow-up questions
- Document acceptance criteria
Step 2: Check Git History
- Search for similar features:
git log --all --oneline --grep="<feature>" - Search for related code changes:
git log -p --all -S "<pattern>" - Identify past solutions and patterns
- Note any blockers encountered previously
- Reference relevant commits for context
Step 3: Explore Codebase
- Use Glob to find relevant files:
glob "**/<pattern>" - Use Grep to find related code:
grep "<pattern>" - Identify existing patterns and conventions
- Locate reusable components and utilities
- Map component dependencies
Step 4: Create Task Breakdown
- Decompose into atomic, testable units
- Define clear deliverables for each task
- Establish task order and dependencies
- Assign to appropriate pipeline agents:
@LeadDeveloper- Core implementation@FrontendDeveloper- UI components@SDETEngineer- Test creation@SystemAnalyst- Architecture decisions
Step 5: Estimate Complexity
- Rate each task: Simple (1-2h), Medium (2-4h), Complex (4h+)
- Consider technical debt and refactoring needs
- Account for testing and documentation
- Add buffer for unexpected issues (20%)
Step 6: Identify Dependencies
- List external dependencies (libraries, APIs, services)
- Identify internal dependencies (modules, components)
- Flag blocking dependencies
- Suggest parallel vs sequential execution paths
Output Format
# Implementation Plan: [Feature Name]
## Summary
[Brief description of what will be built]
## Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2
- [ ] Criterion 3
## Task Breakdown
### Task 1: [Task Name]
- **Agent**: @LeadDeveloper
- **Complexity**: Simple/Medium/Complex
- **Dependencies**: None/List dependencies
- **Deliverables**: [What will be delivered]
- **Files affected**: [List files to modify]
### Task 2: [Task Name]
...
## Technical Decisions
- [Key decisions and rationale]
## Risks & Mitigations
- **Risk**: [Description] → **Mitigation**: [Strategy]
## Estimated Timeline
- Total: X hours
- Breakdown by phase
Best Practices
- Keep plans actionable and specific
- Include file paths and line references where applicable
- Reference existing code patterns
- Consider security implications early
- Plan for error handling and edge cases