# Harness Designer

> Define hook, audit, eval, and checkpoint assets for suite-style Agent Skills packages. Use when a generated suite needs lifecycle guardrails or evaluation scaffolds.

- Skill: `nahisaho/harness-designer` (Agent Skill)
- Install (CLI): `npx skillmds@latest add nahisaho/harness-designer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/nahisaho/harness-designer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: nahisaho (https://skillmd.com/u/nahisaho)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/nahisaho/harness-designer

---


# Harness Designer

## Responsibilities

- Select `minimal`, `standard`, or `strict` harness posture.
- Define which hook scripts and command docs are required.
- Keep harness assets aligned with the orchestration topology.

## Profile Rules

| Profile | Use When | Expected Assets |
|---------|----------|-----------------|
| `minimal` | Low-control scaffold | Basic hooks and command docs |
| `standard` | Default suite build | Hooks, audit doc, eval and verify commands |
| `strict` | Strong guardrails required | Standard set plus config-protection hooks |