init-harness
Creates AI agent task management structure with feature backlog (ai/tasks/), TDD enforcement, and progress tracking. Use when setting up agent-foreman, initializing feature-driven development, creating task backlog, or enabling TDD mode. Triggers on 'init harness', 'setup feature tracking', 'create feature backlog', 'enable strict TDD', 'initialize agent-foreman'.
When & Why to Use This Skill
The Init Harness skill is a specialized utility designed to bootstrap a structured environment for AI agents within a software project. It automates the creation of a comprehensive task management system, including a feature backlog, progress tracking logs, and AI-specific instructions (CLAUDE.md). By enforcing Test-Driven Development (TDD) workflows and providing auto-detection of project architecture, it ensures that AI agents operate with high precision, accountability, and alignment with existing codebases.
Use Cases
- AI-Driven Feature Development: Use the 'init-harness' to create a modular task backlog in the ai/tasks/ directory, allowing AI agents to systematically implement features with clear progress tracking.
- Strict Quality Assurance: Enable 'Strict TDD' mode during initialization to ensure that AI agents cannot mark tasks as complete without writing and passing corresponding tests, maintaining high code standards.
- Legacy Project Onboarding: Run the tool with the --analyze flag on existing repositories to automatically generate ARCHITECTURE.md and CLAUDE.md, giving AI agents the necessary context to contribute to complex, pre-existing codebases.
- Cross-Functional Automation: Deploy specialized task structures for non-coding workflows, such as 'Ops' for runbooks, 'Data' for ETL pipelines, or 'Infra' for cloud provisioning, tailoring the agent's environment to the specific domain.
| name | init-harness |
|---|---|
| description | Creates AI agent task management structure with feature backlog (ai/tasks/), TDD enforcement, and progress tracking. Use when setting up agent-foreman, initializing feature-driven development, creating task backlog, or enabling TDD mode. Triggers on 'init harness', 'setup feature tracking', 'create feature backlog', 'enable strict TDD', 'initialize agent-foreman'. |
| allowed-tools | [Bash, Read, Glob, Grep, Write, Edit] |
| user-invocable | true |
⚡ Init Harness
One command: agent-foreman init
Quick Start
agent-foreman init
Creates: ai/tasks/, ai/progress.log, ai/init.sh, CLAUDE.md
TDD Mode (Default: Recommended)
During init, you'll be prompted for TDD mode. Recommended is the default (tests suggested but not required).
| User Says | TDD Mode | Effect |
|---|---|---|
| "strict TDD" / "require tests" | strict |
Tests REQUIRED - check/done fail without tests |
| "recommended" / "optional tests" / (default) | recommended |
Tests suggested but not enforced |
| "disable TDD" / "no TDD" | disabled |
No TDD guidance |
The prompt auto-skips after 10 seconds with recommended mode.
Modes
| Mode | Command | Effect |
|---|---|---|
| Merge (default) | agent-foreman init |
Keep existing + add new features |
| Fresh | agent-foreman init --mode new |
Replace all features |
| Preview | agent-foreman init --mode scan |
Show without changes |
Task Types
| Type | Command | Use Case |
|---|---|---|
| Code (default) | agent-foreman init |
Software development |
| Ops | agent-foreman init --task-type ops |
Operational tasks, runbooks |
| Data | agent-foreman init --task-type data |
ETL, data pipelines |
| Infra | agent-foreman init --task-type infra |
Infrastructure provisioning |
| Manual | agent-foreman init --task-type manual |
Manual-only verification |
Auto-Detection
ARCHITECTURE.mdexists → use it (fast)- Source code exists → AI scan + auto-save ARCHITECTURE.md
- Empty project → generate from goal
Pre-Init (Recommended)
For existing projects:
agent-foreman init --analyze # First: understand project
agent-foreman init # Then: create harness
Created Files
ai/
├── tasks/ # Task backlog (modular markdown)
│ ├── index.json # Task index
│ └── {module}/ # Module directories
│ └── {id}.md # Individual tasks
├── progress.log # Session audit log
├── init.sh # Bootstrap script
└── capabilities.json # Detected test/lint/build
CLAUDE.md # AI agent instructions
docs/ARCHITECTURE.md # Auto-generated architecture doc