mirror of
https://github.com/cexll/myclaude.git
synced 2026-02-05 02:30:26 +08:00
## Changes ### Core Improvements 1. **Flexible Task Count**: Remove 2-5 hard limit, use natural functional boundaries (typically 2-8) 2. **Complexity-Based Routing**: Tasks rated as simple/medium/complex based on functional requirements 3. **Intelligent Backend Selection**: Orchestrator auto-selects backend based on complexity - Simple/Medium → claude (fast, cost-effective) - Complex → codex (deep reasoning) - UI → gemini (enforced) ### Modified Files - `dev-workflow/agents/dev-plan-generator.md`: - Add complexity field to task template - Add comprehensive complexity assessment guide - Update quality checks to include complexity validation - Remove artificial task count limits - `dev-workflow/commands/dev.md`: - Add backend selection logic in Step 4 - Update task breakdown to include complexity ratings - Add detailed examples for each backend type - Update quality standards - `dev-workflow/README.md`: - Update documentation to reflect intelligent backend selection - Add complexity-based routing explanation - Update examples with complexity ratings ## Architecture - No changes to codeagent-wrapper (all logic in orchestrator) - Backward compatible (existing workflows continue to work) - Complexity evaluation based on functional requirements, NOT code volume ## Benefits - Better resource utilization (use claude for most tasks, codex for complex ones) - Cost optimization (avoid using expensive codex for simple tasks) - Flexibility (no artificial limits on task count) - Clear complexity rationale for each task Generated with swe-agent-bot Co-Authored-By: swe-agent-bot <agent@swe-agent.ai>
/dev - Minimal Dev Workflow
Overview
A freshly designed lightweight development workflow with no legacy baggage, focused on delivering high-quality code fast.
Flow
/dev trigger
↓
AskUserQuestion (requirements clarification)
↓
codeagent analysis (plan mode + UI auto-detection)
↓
dev-plan-generator (create dev doc)
↓
codeagent concurrent development (intelligent backend selection)
↓
codeagent testing & verification (≥90% coverage)
↓
Done (generate summary)
The 6 Steps
1. Clarify Requirements
- Use AskUserQuestion to ask the user directly
- No scoring system, no complex logic
- 2–3 rounds of Q&A until the requirement is clear
2. codeagent Analysis & UI Detection
- Call codeagent to analyze the request in plan mode style
- Extract: core functions, technical points, task list with complexity ratings
- UI auto-detection: needs UI work when task involves style assets (.css, .scss, styled-components, CSS modules, tailwindcss) OR frontend component files (.tsx, .jsx, .vue); output yes/no plus evidence
3. Generate Dev Doc
- Call the dev-plan-generator agent
- Produce a single
dev-plan.md - Append a dedicated UI task when Step 2 marks
needs_ui: true - Include: task breakdown, file scope, dependencies, test commands
4. Concurrent Development
- Work from the task list in dev-plan.md
- Use codeagent per task with intelligent backend selection:
- Simple/Medium tasks →
--backend claude(fast, cost-effective) - Complex tasks →
--backend codex(deep reasoning) - UI tasks →
--backend gemini(enforced)
- Simple/Medium tasks →
- Backend selected automatically based on task complexity rating
- Independent tasks → run in parallel
- Conflicting tasks → run serially
5. Testing & Verification
- Each codeagent task:
- Implements the feature
- Writes tests
- Runs coverage
- Reports results (≥90%)
6. Complete
- Summarize task status
- Record coverage
Usage
/dev "Implement user login with email + password"
No options, fixed workflow, works out of the box.
Output Structure
.claude/specs/{feature_name}/
└── dev-plan.md # Dev document generated by agent
Only one file—minimal and clear.
Core Components
Tools
- AskUserQuestion: interactive requirement clarification
- codeagent skill: analysis, development, testing; supports
--backendfor claude/codex/gemini - dev-plan-generator agent: generate dev doc with complexity ratings (subagent via Task tool, saves context)
Intelligent Backend Selection
- Complexity-based routing: Tasks are rated as simple/medium/complex based on functional requirements (NOT code volume)
- Simple: Follows existing patterns, deterministic logic → claude
- Medium: Requires design decisions, multiple scenarios → claude
- Complex: Architecture design, algorithms, deep domain knowledge → codex
- UI: Style/component work → gemini (enforced)
- Flow impact: Step 2 analyzes complexity; Step 3 includes complexity ratings in dev-plan.md; Step 4 auto-selects backend
- Implementation: Orchestrator reads complexity field and invokes codeagent skill with appropriate backend parameter
Key Features
✅ Fresh Design
- No legacy project residue
- No complex scoring logic
- No extra abstraction layers
✅ Minimal Orchestration
- Orchestrator controls the flow directly
- Only three tools/components
- Steps are straightforward
✅ Concurrency
- Tasks split based on natural functional boundaries
- Auto-detect dependencies and conflicts
- codeagent executes independently with optimal backend
✅ Quality Assurance
- Enforces 90% coverage
- codeagent tests and verifies its own work
- Automatic retry on failure
Example
# Trigger
/dev "Add user login feature"
# Step 1: Clarify requirements
Q: What login methods are supported?
A: Email + password
Q: Should login be remembered?
A: Yes, use JWT token
# Step 2: codeagent analysis
Output:
- Core: email/password login + JWT auth
- Task 1: Backend API (complexity: medium)
- Task 2: Password hashing (complexity: simple)
- Task 3: Frontend form (complexity: simple)
UI detection: needs_ui = true (tailwindcss classes in frontend form)
# Step 3: Generate doc
dev-plan.md generated with complexity ratings ✓
# Step 4-5: Concurrent development (intelligent backend selection)
[task-1] Backend API (claude, medium) → tests → 92% ✓
[task-2] Password hashing (claude, simple) → tests → 95% ✓
[task-3] Frontend form (gemini, UI) → tests → 91% ✓
Directory Structure
dev-workflow/
├── README.md # This doc
├── commands/
│ └── dev.md # /dev workflow orchestrator definition
└── agents/
└── dev-plan-generator.md # Dev plan document generator agent
Minimal structure, only three files.
When to Use
✅ Good for:
- Any feature size
- Fast iterations
- High test coverage needs
- Wanting concurrent speed-up
Design Principles
- KISS: keep it simple
- Disposable: no persistent config
- Quality first: enforce 90% coverage
- Concurrency first: leverage codeagent
- No legacy baggage: clean-slate design
Philosophy: zero tolerance for complexity—ship the smallest usable solution, like Linus would.