# lopopolo/harness-engineering

🐎 Ryan Lopopolo’s anthology, field guide, and agent context bundle for harness engineering

Repository: https://github.com/lopopolo/harness-engineering
Canonical: https://ross.abutalabs.com/products/lopopolo-harness-engineering
Homepage: https://openai.com/index/harness-engineering/
Language: Python
License: CC-BY-4.0
License Family: other
Last push: 2026-07-18T21:55:49+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 93, release rhythm 61, longevity 3
- inputs: {"age_days": 46, "days_push": 46, "days_rel": 46, "gap_med": null, "n_releases_24m": 1}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2614, forks 270 (observed 2026-08-28T04:07:02.920335+00:00)

## What it is
An anthology, field guide, and agent context bundle by Ryan Lopopolo on harness engineering—the practice of improving AI coding agent output by curating context, tools, and the surrounding environment rather than changing the model. It packages essays, talks, and documentation designed to be fed directly to coding agents as retrievable context.

## Use cases
- improve coding agent output quality
- learn harness engineering practices
- point my AI agent at curated context
- make the repository teach the agent
- build feedback loops for agent-driven development
- encode nonfunctional requirements for agents
- ship software with agents writing all the code

## When to choose
- you run AI coding agents (e.g. Codex, Claude Code) and want better reliability and output quality
- you want a written methodology for agent-first software development
- you need an agent context bundle to inject into your coding agent's environment

## When to avoid
- you need executable software or a library to install
- you are not using AI coding agents in your workflow
- you want a neutral multi-vendor guide rather than one author's perspective

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, prompt-engineering, agent-framework, developer-tools
- domain: artificial-intelligence, developer-tools, tutorials, documentation
- platform: python, cross-platform
- tags: harness-engineering, ai-coding-agents, agent-context, codex, agentic-workflows, nonfunctional-requirements, anthology, field-guide, ai-agents

## Member repositories
- lopopolo/harness-engineering (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:02.920335+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:20:34.240593+00:00, confidence not recorded.
  - readme: https://github.com/lopopolo/harness-engineering (fetched 2026-08-28T04:07:02.920335+00:00, sha 975fb89aa2c7)
  - homepage: https://openai.com/index/harness-engineering/ (fetched 2026-08-29T10:03:32.114915+00:00, sha 759c12980dc0)
  - site_page: https://openai.com/about (fetched 2026-08-29T10:03:32.124857+00:00, sha de4b627b33e3)
  - site_page: https://developers.openai.com/api/docs (fetched 2026-08-29T10:03:32.126649+00:00, sha d617c5215f2a)
  - site_page: https://developers.openai.com/ (fetched 2026-08-29T10:03:32.128745+00:00, sha 7d240c906018)
- Data as of 2026-08-30T08:39:29.467469+00:00.