broomvabroomva/harness-engineering/SKILL.md

harness-engineering-playbook

Skill25 starsChanged 8 months agoMITView on GitHub

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.

2 other projects use a version of this.

Adopted by

Most recently taken up by

microsoft/experiment-catalogtheir own version, first seen Jun 16, 2026
broomva/skillstheir own version, first seen Jun 13, 2026

Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
microsoft/experiment-catalog★ 8same name
broomva/skills★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Iterate: after real agent runs — patch gaps and re-audit.
line 30

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

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

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

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

Quick Start

# Interactive wizard (recommended)
python3 .agents/skills/harness-engineering-playbook/scripts/harness_wizard.py init <repo-path> --profile control

# Shell fallback
./scripts/bootstrap_harness.sh <repo-path>

# Audit
python3 .agents/skills/harness-engineering-playbook/scripts/harness_wizard.py audit <repo-path>

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: https://openai.com/index/harness-engineering/

License

MIT

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free