# Agent Harness Builder

Builds and audits harnesses that keep coding agents reliable across sessions.

- Repository: https://github.com/walkinglabs/learn-harness-engineering (22814 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-10-22
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add walkinglabs/learn-harness-engineering --skill harness-creator -g -a claude-code -y`
Codex: `npx skills add walkinglabs/learn-harness-engineering --skill harness-creator -g -a codex -y`
Cursor: `npx skills add walkinglabs/learn-harness-engineering --skill harness-creator -g -a cursor -y`
Gemini CLI: `npx skills add walkinglabs/learn-harness-engineering --skill harness-creator -g -a gemini-cli -y`

## Description

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is unreliable across sessions, forgets context, drifts out of scope, claims "done" before tests pass, or starts each session inconsistently, or when creating or assessing AGENTS.md, CLAUDE.md, feature_list.json, init.sh, progress.md, or session-handoff files. Reach for it even if the user never says the word "harness.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Harness Creator

Use this skill to make a repository easier for coding agents to start, stay in scope, verify work, and resume across sessions. Keep the harness small enough that agents actually follow it.

Not for model selection, prompt tuning in isolation, chat UI design, or general app architecture.

## Core Model

Every useful coding-agent harness has five subsystems:

| Subsystem | Minimal artifact | Purpose |
|---|---|---|
| Instructions | `AGENTS.md` or `CLAUDE.md` | Startup path, working rules, definition of done |
| State | `feature_list.json`, `progress.md` | Current feature, status, evidence, next step |
| Verification | `init.sh` or documented commands | Tests/checks the agent must run before claiming done |
| Scope | Feature dependencies and done criteria | Prevents overreach and half-finished work |
| Lifecycle | `session-handoff.md`, end-of-session routine | Makes the next session restartable |

## First Move

1. Inspect what already exists: instruction files, feature/state files, verification commands, docs, package manifests.
2. Ask only for missing context that cannot be inferred safely: target agent, desired file name, tolerance for structure, and whether overwriting is allowed.
3. Prefer a minimal harness first. Add memory, tool safety, multi-agent, or benchmark details only when the user's problem calls for them.

## Common Tasks

### Create a harness

Use the bundled script when working on a local repository:

```bash
node skills/harness-creator/scripts/create-harness.mjs --target /path/to/project
```

Options:

- `--agent-file CLAUDE.md` for Claude-oriented projects.
- `--package-manager npm|pnpm|yarn|bun` when detection is wrong.
- `--commands "cmd one,cmd two"` for custom verification.
- `--force` only after confirming overwrites are acceptable.

Then explain what was created and how the user should replace placeholder feature entries.

### Audit an existing harness

Run:

The rest: https://github.com/walkinglabs/learn-harness-engineering/blob/HEAD/skills/harness-creator/SKILL.md