harness-init

Initialize a persistent agent harness with git identity and project scaffolding.

19|7|Updated Jan 13, 2026
One-click install
npx skills add https://github.com/oeftimie/vv-claude-harness --skill harness-init-oeftimie
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: harness-init
Source: https://github.com/oeftimie/vv-claude-harness/tree/main/claude/skills/harness-init
Command: npx skills add https://github.com/oeftimie/vv-claude-harness --skill harness-init-oeftimie

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The harness-init skill eliminates fragile, one-shot agent workflows by bootstrapping a persistent project harness that preserves intent, enforces quality gates, and restores context across multi-session AI development.

Core Features & Use Cases

  • Scaffolding: Creates a .harness directory with harness.json, features.json, context_summary.md, claude-progress log, and an init.sh tuned to the detected stack.
  • Quality gates & hooks: Installs PreToolUse, PostToolUse, TaskCompleted, TeammateIdle, and PostCompact hooks under .claude to enforce scope, git identity, and automated test verification.
  • Team & task coordination: Suggests Agent Teams structures, proposes initial features with scopes and dependencies, and records git identity to prevent push/pull mistakes.
  • Use Case: When starting a long-running project with Claude Code, run this initializer to enforce TDD, prevent context loss, and automate sanity checks each session.

Quick Start

Run the harness initializer, confirm the detected git identity and stack, and approve installing the .claude hooks to create the project scaffolding.

Frequently Asked Questions about harness-init

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up persistent context for multi-session AI development?

To set up persistent context for multi-session AI development, initialize a long-running agent harness that captures git identity, creates project scaffolding, and installs shell hook scripts to restore context across sessions.

Can I enforce test-driven development automatically when using Claude Code?

Yes, you can enforce test-driven development automatically by installing PostToolUse and TaskCompleted hooks that run smoke and full tests via an init.sh script, ensuring automated test verification after every agent action.

How do I prevent git push and pull mistakes during automated agent workflows?

Prevent git push and pull mistakes during automated agent workflows by recording your git identity in the project harness metadata, which validates the author before any version control operations are executed.

What is an agent harness and when do I need one for feature tracking?

An agent harness is persistent project scaffolding containing feature tracking, context summaries, and quality gates. You need one when starting a new codebase requiring sustained, multi-session AI development workflows.

Does the harness scaffolding work with Agent Teams coordination?

Yes, the harness scaffolding supports Agent Teams coordination by suggesting team structures, proposing initial features with scopes and dependencies, and utilizing TeammateIdle hooks for synchronized agent workflows.

What are the limitations of bootstrapping a project harness for AI code generation?

Bootstrapping a project harness requires an existing git repository to capture identity and detect the stack, meaning it cannot scaffold projects in empty directories without version control initialized first.