# Harness Engineering Playbook

> Implement OpenAI Harness Engineering practices in any repository — AGENTS.md, PLANS.md, deterministic smoke/test/lint harness commands, strict architecture boundaries, observability from day 1, and entropy-control audits for reliable autonomous agent runs.

- **Type:** Skill
- **Install:** `agentstack add skill-broomva-harness-engineering-harness-engineering`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [broomva](https://agentstack.voostack.com/s/broomva)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [broomva](https://github.com/broomva)
- **Source:** https://github.com/broomva/harness-engineering

## Install

```sh
agentstack add skill-broomva-harness-engineering-harness-engineering
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Harness Engineering Playbook

A skills.sh-compatible skill that operationalizes the practices from OpenAI's Harness Engineering guide. Use it to set up or refactor agent-first workflows so that autonomous runs are repeatable, observable, and safe.

## Install

```bash
npx skills add broomva/harness-engineering-skill --skill harness-engineering-playbook
```

## What It Does

- Bootstraps harness artifacts: `AGENTS.md`, `PLANS.md`, `docs/ARCHITECTURE.md`, `docs/OBSERVABILITY.md`, `Makefile.harness`, and CI workflows.
- Wraps deterministic commands behind `make smoke`, `make check`, `make ci` so agents can run them reliably.
- Enforces strict module boundaries and data-shape contracts.
- Wires structured observability (correlation IDs, key transitions) from day 1.
- Adds entropy-control audits and nightly harness checks to prevent docs drift and flaky scripts.

## Workflow

1. **Baseline** the target repo — detect language, toolchain, and existing CI.
2. **Bootstrap** harness artifacts from templates (interactive wizard or shell script).
3. **Apply** the nine Harness Engineering practices across repo artifacts.
4. **Validate** with `audit` — treat any `MISSING` or `FAIL` as blocking.
5. **Iterate** after real agent runs — patch gaps and re-audit.

## Quick Start

```bash
# Interactive wizard (recommended)
python3 .agents/skills/harness-engineering-playbook/scripts/harness_wizard.py init  --profile control

# Shell fallback
./scripts/bootstrap_harness.sh 

# Audit
python3 .agents/skills/harness-engineering-playbook/scripts/harness_wizard.py audit 
```

## Profiles

| Profile    | Scope                                              |
|------------|----------------------------------------------------|
| `baseline` | Core harness artifacts only                        |
| `control`  | Baseline + control-system primitives               |
| `full`     | Control + entropy controls, nightly audit, CI      |

## Source

OpenAI Harness Engineering guide: 

## License

MIT

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [broomva](https://github.com/broomva)
- **Source:** [broomva/harness-engineering](https://github.com/broomva/harness-engineering)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-broomva-harness-engineering-harness-engineering
- Seller: https://agentstack.voostack.com/s/broomva
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.