7.5 KiB
7.5 KiB
| description | argument-hint | allowed-tools |
|---|---|---|
| Execute tasks in parallel waves with optimal agent selection and review | <task list or "from todo"> | Task, Read, Write, Edit, Glob, Grep, Bash, TodoWrite |
Execute these tasks in parallel waves with proper review: $ARGUMENTS
Instructions
Load the orchestrated-execution skill, then:
Philosophy: Do It Right
Take your time. No shortcuts. Every implementation should be:
- Clean - Readable, well-named, minimal complexity
- Maintainable - Future developers can understand and modify it
- Extensible - Easy to add features without rewriting
- Refactored - If existing code is messy, clean it up as you go
When you encounter code that could be better:
- Refactor it. Don't work around bad patterns.
- Extract helpers, rename unclear variables, simplify nesting
- Leave the codebase better than you found it
Prefer proper solutions over quick fixes. A 50-line clean implementation beats a 10-line hack.
Phase 1: Parse & Analyze
- Parse tasks - From todo list or provided
- Analyze dependencies - Which tasks depend on which
- Group into waves - Tasks without mutual dependencies go in same wave
Phase 2: Wave Planning
For each wave, determine:
## Wave [N]
| Task | Implementer | Why | Reviewer | Why |
|------|-------------|-----|----------|-----|
| [Name] | [Agent] | [domain match] | [Agent] | [risk match] |
**Parallelizable because:** [No dependencies between these tasks]
**Blocked until:** [Wave N-1 complete] or [Nothing]
Present the wave plan to user before executing.
Phase 3: Execute Each Wave
Wave N:
┌─────────────────────────────────────────────┐
│ 1. LAUNCH ALL IMPLEMENTERS (parallel) │
│ │
│ Task(agent1, task1) ──┐ │
│ Task(agent2, task2) ──┼── concurrent │
│ Task(agent3, task3) ──┘ │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ 2. COLLECT RESULTS │
│ Wait for all to complete │
│ Gather implementation outputs │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ 3. LAUNCH ALL REVIEWERS (parallel) │
│ │
│ Task(reviewer1, review1) ──┐ │
│ Task(reviewer2, review2) ──┼── concurrent│
│ Task(reviewer3, review3) ──┘ │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ 4. PROCESS REVIEW RESULTS │
│ │
│ PASS → mark complete │
│ NEEDS_FIX → fix loop (can parallelize) │
│ BLOCK → escalate immediately │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ 5. VERIFY WAVE COMPLETE │
│ All tasks in wave done? │
│ Any conflicts from parallel execution? │
└─────────────────────────────────────────────┘
│
▼
Continue to Wave N+1
Phase 4: Loose Ends (Critical for Parallel)
After all waves, explicitly check:
- File conflicts - Did parallel tasks modify same files?
- Integration gaps - Do the pieces work together?
- Merge issues - Any conflicting changes to resolve?
- Cross-cutting - Consistent patterns across all tasks?
- Quality gate - Full build, test, lint
Phase 5: Final Report
## Parallel Execution Complete
### Wave Summary
| Wave | Tasks | Parallel Time | Status |
|------|-------|---------------|--------|
| 1 | 3 | ~2min | ✓ |
| 2 | 2 | ~1min | ✓ |
| 3 | 1 | ~1min | ✓ |
### Task Details
| Task | Wave | Implementer | Reviewer | Issues Fixed | Status |
|------|------|-------------|----------|--------------|--------|
### Loose Ends Resolved
- [Conflicts fixed]
- [Integration issues addressed]
### Quality Gate
- Build: PASS
- Tests: PASS
- Lint: PASS
Dependency Detection
Tasks depend on each other when:
Task A: "Create User model"
Task B: "Add validation to User model" ← Depends on A
Task A: "Implement auth backend"
Task B: "Write auth tests" ← Depends on A
Task A: "Update config schema"
Task B: "Migrate existing configs" ← Depends on A
Tasks are independent when:
Task A: "Add logging to ingestion"
Task B: "Add metrics to query" ← Different modules, independent
Task A: "Write User docs"
Task B: "Write Config docs" ← Different files, independent
Agent Selection
Implementers
| Task Type | Agent |
|---|---|
| Go code, features | go-specialist |
| Tests | testing-strategist |
| API design | api-designer |
| Database | database-architect |
| K8s, deployment | worker-specialist |
| Security, auth | security-architect |
| Architecture | hexagonal-architect |
| Docs | librarian |
Reviewers
| Risk Type | Reviewer |
|---|---|
| Code quality | quality-engineer |
| Security | security-architect |
| Architecture | hexagonal-architect |
| Test coverage | testing-strategist |
Wave Progress Format
## Wave 2 Progress
### Implementing (parallel)
→ Task 4: auth-backend - go-specialist
→ Task 5: rate-limiter - security-architect
→ Task 6: metrics - go-specialist
### Wave 1 Complete
✓ Task 1: user-model - go-specialist ✓ quality-engineer
✓ Task 2: config-schema - go-specialist ✓ quality-engineer
✓ Task 3: docs-update - librarian ✓ librarian
Critical Rules
- NEVER put dependent tasks in same wave
- ALWAYS review even in parallel mode
- ALWAYS check for conflicts after parallel execution
- ALWAYS run quality gate at the end
- ANNOUNCE wave plan before executing
- MAX 3 fix cycles per task, then escalate
Step Back: Before Each Wave
- Dependencies verified? Wave N-1 complete?
- No conflicts anticipated? Parallel tasks won't clash?
- Right agents selected? Re-check before launching
- Rollback plan? If wave fails, how do we recover?
Step Back: After Each Wave
- All tasks actually complete? Not just "launched"
- Reviews actually done? Not skipped for speed
- Issues actually fixed? Not deferred
- No file conflicts? From parallel writes