Individual skill
harness-engineering-playbook
Implement OpenAI Harness Engineering practices in any repository. Use when setting up or refactoring agent-first workflows, writing or upgrading AGENTS.md and PLANS.md, creating deterministic smoke/test/lint/typecheck harness commands, defining strict architecture boundaries and data-shape contracts, wiring observability from day 1, and adding entropy-control checks plus CI automation for reliable autonomous runs.
.skills/harness-engineering-playbook/SKILL.md
Source commit 12d68503307a2843f29d7043adfdbc3045378723
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 5, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 26
- Repository last updated
- Jun 28, 2026
- License
- MIT
Observed agent integration: codex
- agent-skills Repository topic
- openai-codex Repository topic
- skills-sh Repository topic
- harness-engineering Repository topic
- bstack-foundation Repository topic
- autonomous-agents Repository topic
- ci-cd Repository topic
- developer-tools Repository topic
- engineering Derived category
- writing Derived category
- data Derived category
- testing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 5,420 bytesSKILL.mdcore · 5,420 bytesSKILL.mdcore · 5,420 bytesagents/openai.yamlasset · 281 bytesassets/templates/.github/workflows/harness.ymlasset · 434 bytesassets/templates/.github/workflows/nightly-harness-audit.ymlasset · 417 bytesassets/templates/AGENTS.mddoc · 1,849 bytesassets/templates/Makefile.harnessasset · 240 bytesassets/templates/PLANS.mddoc · 811 bytesassets/templates/docs/ARCHITECTURE.mddoc · 1,086 bytesassets/templates/docs/OBSERVABILITY.mddoc · 894 bytesassets/templates/docs/control/ACTUATORS.mddoc · 643 bytesassets/templates/docs/control/CONTROLLER.mddoc · 508 bytesassets/templates/docs/control/CONTROL_SYSTEM.mddoc · 444 bytesassets/templates/docs/control/ENTROPY.mddoc · 561 bytesassets/templates/docs/control/FEEDBACK_LOOP.mddoc · 437 bytesassets/templates/docs/control/SENSORS.mddoc · 685 bytesassets/templates/docs/control/SETPOINTS.mddoc · 392 bytesassets/templates/docs/control/STABILITY.mddoc · 697 bytesassets/templates/evals/control-loop-metrics.yamlasset · 584 bytesassets/templates/scripts/audit_harness.shruns · 2,380 bytesassets/templates/scripts/harness/entropy_check.shruns · 1,248 bytesassets/templates/scripts/harness/lint.shruns · 973 bytesassets/templates/scripts/harness/smoke.shruns · 1,060 bytesassets/templates/scripts/harness/test.shruns · 843 bytesassets/templates/scripts/harness/typecheck.shruns · 1,115 bytesreferences/openai-harness-practices.mddoc · 2,847 bytesreferences/rollout-checklist.mddoc · 1,625 bytesreferences/wizard-cli.mddoc · 1,619 bytesscripts/audit_harness.shruns · 2,372 bytesscripts/bootstrap_harness.shruns · 2,764 bytesscripts/harness_wizard.pyruns · 7,311 bytes
Read excerpt
# Harness Engineering Playbook
Use this skill to operationalize the practices from OpenAI's Harness Engineering guide in a repo that agents can run against repeatedly and safely.
## What To Load
- Use `references/openai-harness-practices.md` for the full practice-to-artifact mapping.
- Use `references/rollout-checklist.md` for phased adoption in active repos.
- Use `references/wizard-cli.md` for Typer wizard command flows.
- Use `assets/templates/` when creating or updating harness files.
## Inputs
- Target repository path.