init-harness
It sets up standardized directory structures and task management systems to support test-driven development workflows.
Install
mkdir -p .claude/skills/init-harness && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9326" && unzip -o skill.zip -d .claude/skills/init-harness && rm skill.zipInstalls to .claude/skills/init-harness
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
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'.Key capabilities
- →Generates directory structure for feature backlog and logging
- →Enforces TDD-based development flow via CLI prompts
- →Provides automated ARCHITECTURE.md generation from source
- →Supports specialized project modes for Ops, Data, and Infra tasks
- →Offers preview mode to validate changes before execution
How it works
It executes a shell script that scaffolds files and prompts the user for TDD enforcement levels before applying the directory layout.
Inputs & outputs
When to use init-harness
- →Setting up agent-foreman
- →Initializing feature backlogs
- →Enabling strict TDD mode
- →Setting up operational runbooks
About this skill
⚡ 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
When not to use it
- →In projects where external CI/CD already manages task backlogs
- →For trivial scripts where directory structure overhead is unnecessary
Prerequisites
Limitations
- →Requires manual CLI interaction during the 10-second prompt window
- →Overwrites specific configuration files if mode is set to 'new'
- →Limited by the accuracy of the auto-generated ARCHITECTURE.md
How it compares
It replaces manual directory scaffolding and manual TDD enforcement with an automated, policy-aware CLI agent flow.
Compared to similar skills
init-harness side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| init-harness (this skill) | 0 | 6mo | Review | Beginner |
| archon | 0 | 26d | Review | Intermediate |
| parallel | 0 | 3mo | Review | Advanced |
| agentic-jujutsu | 3 | 4mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by mylukin
View all by mylukin →You might also like
archon
coleam00
|
parallel
zhukunpenglinyutong
Multi-agent pipeline orchestrator that plans and dispatches parallel development tasks to worktree agents. Reads project context, configures task directories with PRDs and jsonl context files, and launches isolated coding agents. Use when multiple independent features need parallel development, orch
agentic-jujutsu
ruvnet
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
skillshare
runkids
Syncs skills across AI CLI tools (Claude, Cursor, Windsurf, etc.) from a single source of truth. Use when: "sync skills", "install skill", "search skills", "list skills", "show skill status", "backup skills", "restore skills", "update skills", "new skill", "collect skills", "push/pull skills", "add/remove target", "find a skill for X", "is there a skill that can...", "how do I do X with skills", "skillshare init", "skillshare upgrade", "skill not syncing", "diagnose skillshare", "doctor", or any skill/target management across AI tools.
moai
modu-ai
MoAI super agent - unified orchestrator for autonomous development. Routes natural language or explicit subcommands (plan, run, sync, fix, loop, project, feedback) to specialized agents. Use for any development task from planning to deployment.
build-with-agent-team
coleam00
Build a project using Claude Code Agent Teams with tmux split panes. Takes a plan document path and optional team size. Use when you want multiple agents collaborating on a build.