Menu

Not in the top 1,000 by GitHub stars

broomva/harness-engineering

Harness Engineering playbook — deterministic smoke/test/lint harness commands, strict architecture boundaries, entropy-control checks for autonomous agent workflows.

CodexEngineeringTesting

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 12d68503307a

No earlier version was observed for comparison.

Compare on GitHub

.skills/harness-engineering-playbook/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 12d68503307a

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 12d68503307a2843f29d7043adfdbc3045378723

git clone --filter=blob:none --no-checkout https://github.com/broomva/harness-engineering.git .hotskills/broomva-harness-engineering && git -C .hotskills/broomva-harness-engineering checkout --detach 12d68503307a2843f29d7043adfdbc3045378723 # Copy each selected skill directory from .hotskills/broomva-harness-engineering into .agents/skills/<skill-name>/
26GitHub stars
0stars in 7 days
2skills in this repository
0commits in 30 days

Heat

0.4
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 202626

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

harness-engineering-playbook

When your agent uses it

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.

What it loads into context

Frontmatter

57 tokens

Always available to the agent

SKILL.md

516 tokens

When the skill is activated

Reference documents

182 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Install
  2. What It Does
  3. Workflow
  4. Quick Start
  5. Profiles
  6. Source
  7. License

Files

  • LICENSEasset1,081 bytes
  • README.mddoc689 bytes
  • SKILL.mdcore2,396 bytes
  • SKILL.mdcore2,396 bytes
  • SKILL.mdcore2,396 bytes
  • SKILL.mdcore2,396 bytes
  • SKILL.mdcore2,396 bytes
Read 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

```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.
View the complete source on GitHub

Skills included

  • harness-engineering-playbook
  • harness-engineering-playbook

Repository facts

License
MIT
Created
Feb 17, 2026
Last pushed
Jun 28, 2026
Forks
0
Open issues
0
Project activity
Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 6 notes
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • .skills/harness-engineering-playbook/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • .skills/harness-engineering-playbook/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 20 signals by file

.skills/harness-engineering-playbook/assets/templates/scripts/audit_harness.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

.skills/harness-engineering-playbook/assets/templates/scripts/harness/entropy_check.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

.skills/harness-engineering-playbook/assets/templates/scripts/harness/lint.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Dangerous shell operationline 8
    eval "$HARNESS_LINT_CMD"

.skills/harness-engineering-playbook/assets/templates/scripts/harness/smoke.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Dangerous shell operationline 8
    eval "$HARNESS_SMOKE_CMD"

.skills/harness-engineering-playbook/assets/templates/scripts/harness/test.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Dangerous shell operationline 8
    eval "$HARNESS_TEST_CMD"

.skills/harness-engineering-playbook/assets/templates/scripts/harness/typecheck.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Dangerous shell operationline 8
    eval "$HARNESS_TYPECHECK_CMD"

.skills/harness-engineering-playbook/references/openai-harness-practices.md

  • Network accessline 7
    - Harness Engineering: https://openai.com/index/harness-engineering/
  • Network accessline 8
    - Using `PLANS.md` for multi-hour tasks: https://cookbook.openai.com/articles/plan-driven-workflow
  • Network accessline 9
    - Data-shape boundary design reference: https://matklad.github.io/2023/08/17/types-are-parse-don-t-validate.html
  • Network accessline 10
    - Boundary-first architecture reference: https://matklad.github.io/2021/02/06/ARCHITECTURE.md.html

.skills/harness-engineering-playbook/scripts/audit_harness.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

.skills/harness-engineering-playbook/scripts/bootstrap_harness.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

.skills/harness-engineering-playbook/scripts/harness_wizard.py

  • Executable scriptline 1
    #!/usr/bin/env python3

README.md

  • Network accessline 3
    > **Status:** 6-month deprecation window (until 2026-12-27). This skill now lives in the > [broomva/skills](https://github.com/broomva/skills) monorepo (BRO-1561 / BRO-1570).
  • Network accessline 4
    > [broomva/skills](https://github.com/broomva/skills) monorepo (BRO-1561 / BRO-1570).

SKILL.md

  • Network accessline 55
    OpenAI Harness Engineering guide: <https://openai.com/index/harness-engineering/>

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Signal confidence: 20 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexNativeManifest .skills/harness-engineering-playbook/assets/templates/AGENTS.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

dzhng/skills

Reusable AI agent skills for software factories: explore ideas, write specs, implement, review, and run autonomous research. Works with Claude Code, Codex, and other skill-compati…

1.4kGitHub stars

See-Sol-Lab/private-house-code-v2.5

让 Codex 少烧 Token、少造复杂度，同时不降智的代码约束 Skill

95GitHub stars

Amey-Thakur/AI-SKILLS

Plug-and-play skills and prompts for every AI coding agent

13GitHub stars

dongshuyan/compass-skills

司南：个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents

764GitHub stars

qshanx/docs-governance

Claude Code、Codex 与 ChatGPT 的文档驱动开发治理插件：防文档腐烂、维护上下文与决策、契约协作、测试与回归证据。

325GitHub stars

osovv/grace-marketplace

GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with semantic markup, knowledge graphs, and support for Claude Code, Codex…

266GitHub stars