How do I install the Harness skill?

Run npx skillmds@latest add zereight/harness in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Harness safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Harness?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Harness free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Harness?

zereight (@zereight) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Harness by zereight — Agent Skill

Name: Harness
Author: zereight

Harness

Pi-native evaluate→improve→persist harness. Provides a systematic loop for generating candidates, judging them against rubrics, and accumulating knowledge as playbooks. Use for iterative output improvement, not for one-off edits (use continuity) or single PR review (use zereight-review).

zereight 9102741 1.9 KB Updated Sep 17, 2026

File contents

harness (Pi-native evaluation loop)

Builds on autoctx (judge/improve core) + Pi tools to provide a coherent harness.

Stack

Layer	Source	Role
Extension	`~/.pi/agent/extensions/harness/index.ts`	Tools + TUI + lifecycle
Judge engine	`autoctx` (via `pi-autocontext` dep)	LLM-based evaluation
Skill	`.agents/skills/harness/SKILL.md`	Usage guide + routing

Tools

Tool	Description
`harness_solve`	Full loop: generate → judge → improve → persist playbook
`harness_knowledge`	Read/write/list playbooks (`knowledge/<scenario>/playbook.md`)
`harness_status`	Recent runs, scores, and scenarios overview

Usage

# Solve a task with rubric-driven improvement
goal: "Improve zereight-review checklist for RN PRs"
rubric: "Actionable findings, Effect anti-patterns, security when relevant"
→ Best output + playbook saved to knowledge/<scenario>/

# Check previous runs
→ Recent runs with scores and scenarios

# Browse accumulated knowledge
action: list → all scenarios with playbooks
action: read, scenario: zereight-review → full playbook

When to use

Need	Use
Systematic output improvement	`harness_solve`
Review accumulated lessons	`harness_knowledge read`
Check past run history	`harness_status`
One-off judge/improve	`autocontext_judge` / `autocontext_improve` (pi-autocontext)

Cost

harness_solve consumes Pi provider quota per generation round.
Start with gens: 1 to calibrate rubric, then increase.
harness_knowledge and harness_status are zero-cost.

---name: harnessdescription: Pi-native evaluate→improve→persist harness. Provides a systematic loop for generating candidates, judging them against rubrics, and accumulating knowledge as playbooks. Use for iterative output improvement, not for one-off edits (use continuity) or single PR review (use zereight-review).---# harness (Pi-native evaluation loop)Builds on autoctx (judge/improve core) + Pi tools to provide a coherent harness.## Stack| Layer | Source | Role ||-------|--------|------|| Extension | `~/.pi/agent/extensions/harness/index.ts` | Tools + TUI + lifecycle || Judge engine | `autoctx` (via `pi-autocontext` dep) | LLM-based evaluation || Skill | `.agents/skills/harness/SKILL.md` | Usage guide + routing |## Tools| Tool | Description ||------|-------------|| `harness_solve` | Full loop: generate → judge → improve → persist playbook || `harness_knowledge` | Read/write/list playbooks (`knowledge/<scenario>/playbook.md`) || `harness_status` | Recent runs, scores, and scenarios overview |## Usage```# Solve a task with rubric-driven improvementgoal: "Improve zereight-review checklist for RN PRs"rubric: "Actionable findings, Effect anti-patterns, security when relevant"→ Best output + playbook saved to knowledge/<scenario>/# Check previous runs→ Recent runs with scores and scenarios# Browse accumulated knowledgeaction: list → all scenarios with playbooksaction: read, scenario: zereight-review → full playbook```## When to use| Need | Use ||------|-----|| Systematic output improvement | `harness_solve` || Review accumulated lessons | `harness_knowledge read` || Check past run history | `harness_status` || One-off judge/improve | `autocontext_judge` / `autocontext_improve` (pi-autocontext) |## Cost- `harness_solve` consumes Pi provider quota per generation round.- Start with `gens: 1` to calibrate rubric, then increase.- `harness_knowledge` and `harness_status` are zero-cost.

Frequently asked questions