# Harness Engineering

> This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR preparation, and human approval boundaries.

## Facts
- Page: https://tashan.sh/capability/skill-guanyang-harness-engineering
- tashan id: skill:guanyang/harness-engineering
- Source: https://github.com/guanyang/open-agent-hub
- Type: skill
- Category: other
- tashan score: 51.0 / 100
- Adoption: 14.0
- Upkeep: 99.0
- Freshness: 97.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: MIT
- Official: no

## Install

```sh
cp -r harness-engineering ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-09-12 by tashan (https://tashan.sh) from public evidence. Scorer s5.