Files
llm-harness/templates/PROJECT-HARNESS.md.template
T

140 lines
3.7 KiB
Plaintext

# PROJECT HARNESS TEMPLATE
**Copy this to your project and customize.**
---
## [Project Name] Structure
```
~/workspace/[project]/
├── HARNESS.md ← This file (project-specific)
├── modules/
│ ├── design/ ← Architecture & planning phase
│ │ ├── SPEC.md ← What to build
│ │ ├── CONSTRAINTS.md ← Non-functional requirements
│ │ ├── SCHEMA.md ← Data model (if applicable)
│ │ └── ARCHITECTURE.md ← System design
│ │
│ ├── implementation/ ← Building phase
│ │ ├── GUIDE.md ← How to build
│ │ ├── CHECKLIST.md ← What to verify
│ │ └── CODE_STANDARDS.md ← Style & patterns
│ │
│ ├── testing/ ← QA phase
│ │ ├── TEST_PLAN.md ← What to test
│ │ ├── CASES.md ← Test cases
│ │ └── COVERAGE.md ← Coverage targets
│ │
│ └── docs/ ← Documentation phase
│ ├── USER_GUIDE.md ← For end users
│ ├── API.md ← For developers
│ └── DEPLOYMENT.md ← For ops
├── [project files/directories]
└── README.md ← Project overview
```
---
## Phases
### Phase 1: Design
- **Agent:** claude-code (opus model)
- **Module:** design/
- **Input:** SPEC.md, CONSTRAINTS.md
- **Output:** ARCHITECTURE.md, SCHEMA.md
- **Validation:** All constraints addressed
### Phase 2: Implementation
- **Agent:** claude-code (sonnet model)
- **Module:** implementation/
- **Input:** ARCHITECTURE.md from Phase 1
- **Output:** Working code
- **Validation:** Passes CODE_STANDARDS.md
### Phase 3: Review
- **Agent:** cursor (opus model)
- **Module:** [code to review]
- **Input:** Implementation from Phase 2
- **Output:** Review report, approved/rejected
- **Validation:** Critical feedback addressed
### Phase 4: Testing
- **Agent:** claude-code (sonnet model)
- **Module:** testing/
- **Input:** TEST_PLAN.md
- **Output:** Test code, coverage report
- **Validation:** Coverage targets met
### Phase 5: Documentation
- **Agent:** claude-code (sonnet model)
- **Module:** docs/
- **Input:** Code + ARCHITECTURE.md
- **Output:** USER_GUIDE.md, API.md, DEPLOYMENT.md
- **Validation:** Complete, accurate, usable
---
## Key Constraints
**[List your project's non-functional requirements]**
- Performance: [e.g., API responses <100ms p95]
- Scalability: [e.g., support 10k concurrent users]
- Security: [e.g., encryption at rest/transit]
- Availability: [e.g., 99.9% uptime SLA]
- Compatibility: [e.g., Node.js 20+, PostgreSQL 14+]
---
## Technology Stack
**Backend:** [e.g., Node.js + Express]
**Database:** [e.g., PostgreSQL + Redis]
**Frontend:** [e.g., React + Tailwind]
**DevOps:** [e.g., Docker + Kubernetes]
---
## Module Loading Rules
When briering agents:
- Only load the CURRENT phase's module
- Don't load future phases
- Include CONSTRAINTS.md in every brief
- Include project README for context
Example: When designing, DON'T load implementation/ or testing/
---
## Checkpoint & Recovery
Each phase saves checkpoint:
```json
{
"phase": "design",
"status": "completed|in_progress|blocked|error",
"timestamp": "2026-04-25T23:00:00Z",
"agent": "claude-code",
"model": "opus",
"result_file": "modules/design/ARCHITECTURE.md",
"next_phase": "implementation"
}
```
If phase fails, save error and replan.
---
## Customization
Change this template to fit YOUR project:
- Add/remove phases
- Change agent assignments
- Define your own constraints
- Add project-specific workflows
Just keep the structure PSR-4 compatible.