mcpField
H
harness-engineering-playbook

harness-engineering-playbook

github.com/broomvaAgent workflows26384 installsUpdated 18w ago
Repository

About harness-engineering-playbook

A skills.sh-compatible skill for teams setting up or refactoring agent-first workflows. It applies Harness Engineering practices through repository templates, deterministic commands, and audits to make autonomous runs repeatable, observable, and safe.

Key features

  1. 01Generate repository harness docs and configuration
  2. 02Wrap smoke, check, and ci commands
  3. 03Set module boundaries and data contracts
  4. 04Add structured observability
  5. 05Audit documentation drift and flaky scripts

Use cases

  1. 01Set up agent workflows in an existing repository
  2. 02Standardize checks for autonomous runs
  3. 03Audit and improve harness configuration

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/broomva/harness-engineering --skill harness-engineering-playbook

After installing, type/harness-engineering-playbookin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

README.md
.skills/harness-engineering-playbook/agents/
openai.yaml
.skills/harness-engineering-playbook/assets/templates/
Makefile.harness
PLANS.md
AGENTS.md
.skills/harness-engineering-playbook/assets/templates/.github/workflows/
harness.yml
nightly-harness-audit.yml
.skills/harness-engineering-playbook/assets/templates/docs/
OBSERVABILITY.md
ARCHITECTURE.md
.skills/harness-engineering-playbook/assets/templates/docs/control/
ACTUATORS.md
CONTROL_SYSTEM.md
ENTROPY.md
CONTROLLER.md
FEEDBACK_LOOP.md
SETPOINTS.md
SENSORS.md
STABILITY.md
.skills/harness-engineering-playbook/assets/templates/evals/
control-loop-metrics.yaml
.skills/harness-engineering-playbook/assets/templates/scripts/
audit_harness.sh
.skills/harness-engineering-playbook/assets/templates/scripts/harness/
entropy_check.sh
lint.sh
smoke.sh
test.sh
typecheck.sh
.skills/harness-engineering-playbook/references/
openai-harness-practices.md
rollout-checklist.md
wizard-cli.md
.skills/harness-engineering-playbook/scripts/
audit_harness.sh
bootstrap_harness.sh
harness_wizard.py

Details

From the project README

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

  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

# 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

ProfileScope
baselineCore harness artifacts only
controlBaseline + control-system primitives
fullControl + entropy controls, nightly audit, CI

Source

OpenAI Harness Engineering guide: https://openai.com/index/harness-engineering/

License

MIT

Comments

Markdown supported