How do I install the Harness Gepa skill?

Run npx skillmds@latest add gabrielmoreira/harness-gepa 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 Gepa safe to use?

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

Which AI agents work with Harness Gepa?

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 Gepa free to use?

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

Who published Harness Gepa?

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

Harness Gepa by gabrielmoreira — Agent Skill

Name: Harness Gepa
Rating: 4.2 (5 reviews)
Author: gabrielmoreira

Harness Gepa

Inspect and audit GEPA genomes via the `@metaharness/darwin/gepa` library entry (darwin 0.8.0) — load/validate a genome (default is the shipped cand-6 promotion), render the system prompt a genome compiles to, or classify failure modes in a run transcript. The `gepaOptimize` loop itself is library-only (bring your own evaluator) and not surfaced here — use `harness-evolve` for sandbox-scored evolution. Degrades gracefully when @metaharness/darwin is absent.

gabrielmoreira Updated Sep 9, 2026 17 repo stars

File contents

Surfaces the GEPA (genetic-evolution prompt-adaptation) library exports from @metaharness/darwin/gepa. Unlike the other skills in this plugin there is no CLI binary behind this — the script dynamic-imports the library (local resolution first, versioned cache install as fallback) and calls the subprocess-safe subset.

When to use

Adopting an evolved policy: --op render shows the actual system prompt a genome compiles to — read THAT, not the raw JSON, before wiring a genome into a harness.
Auditing a promotion: --op genome loads + validates the shipped cand-6 genome (first holdout-confirmed cheap-tier promotion; provenance ships in the package) or any genome file you point at.
CI gate on genome edits: --op validate --alert-on-invalid exits 1 on structural errors.
Debugging a bad run: --op analyze --transcript run.json classifies failure modes (GEPA's failure-class taxonomy) from a transcript array.

What is deliberately NOT here

gepaOptimize — the optimization loop takes an in-process evaluate(candidate) callback ("bring your own evaluator") that cannot cross a subprocess boundary. Two supported paths instead:

Library consumers: import { gepaOptimize, loadCand6Genome } from '@metaharness/darwin/gepa'
Sandbox-scored evolution: harness-evolve (darwin CLI evolve), which pairs GEPA with its own sandbox evaluators.

Algorithm

Implementation: scripts/gepa.mjs.

import('@metaharness/darwin/gepa'); on MODULE_NOT_FOUND fall back to a one-time npm install --prefix ~/.ruflo/darwin-cache-0.8.0 and import the cached dist/gepa/index.js (versioned dir → pin bumps invalidate).
Dispatch --op:
- genome → loadGenome(fs, path) or loadCand6Genome() + validateGenome
- validate → validateGenome(rawJson) (raw parse so broken files reach the validator instead of throwing in the loader)
- render → buildSystemFromGenome(genome, ext?, glob?)
- analyze → analyzeTranscript(entries)
Emit one JSON object; exit 0 (or 1 under --alert-on-invalid, 2 on bad input).

Examples

node scripts/gepa.mjs --op genome                          # cand-6 + validation
node scripts/gepa.mjs --op render | jq -r .system         # what does cand-6 SAY?
node scripts/gepa.mjs --op validate --path my-genome.json --alert-on-invalid
node scripts/gepa.mjs --op analyze --transcript run.json

Exit codes

0 — op completed (or degraded — darwin not installable)
1 — --alert-on-invalid and validation found errors
2 — config error (unknown op, missing/broken input file)

---name: harness-gepadescription: Inspect and audit GEPA genomes via the `@metaharness/darwin/gepa` library entry (darwin 0.8.0) — load/validate a genome (default is the shipped cand-6 promotion), render the system prompt a genome compiles to, or classify failure modes in a run transcript. The `gepaOptimize` loop itself is library-only (bring your own evaluator) and not surfaced here — use `harness-evolve` for sandbox-scored evolution. Degrades gracefully when @metaharness/darwin is absent.--- Surfaces the GEPA (genetic-evolution prompt-adaptation) *library* exports from `@metaharness/darwin/gepa`. Unlike the other skills in this plugin there is no CLI binary behind this — the script dynamic-imports the library (local resolution first, versioned cache install as fallback) and calls the subprocess-safe subset. ## When to use - **Adopting an evolved policy**: `--op render` shows the actual system prompt a genome compiles to — read THAT, not the raw JSON, before wiring a genome into a harness. - **Auditing a promotion**: `--op genome` loads + validates the shipped cand-6 genome (first holdout-confirmed cheap-tier promotion; provenance ships in the package) or any genome file you point at. - **CI gate on genome edits**: `--op validate --alert-on-invalid` exits 1 on structural errors. - **Debugging a bad run**: `--op analyze --transcript run.json` classifies failure modes (GEPA's failure-class taxonomy) from a transcript array. ## What is deliberately NOT here `gepaOptimize` — the optimization loop takes an in-process `evaluate(candidate)` callback ("bring your own evaluator") that cannot cross a subprocess boundary. Two supported paths instead: 1. **Library consumers**: `import { gepaOptimize, loadCand6Genome } from '@metaharness/darwin/gepa'` 2. **Sandbox-scored evolution**: `harness-evolve` (darwin CLI `evolve`), which pairs GEPA with its own sandbox evaluators. ## Algorithm Implementation: [`scripts/gepa.mjs`](../../scripts/gepa.mjs). 1. `import('@metaharness/darwin/gepa')`; on MODULE_NOT_FOUND fall back to a one-time `npm install --prefix ~/.ruflo/darwin-cache-0.8.0` and import the cached `dist/gepa/index.js` (versioned dir → pin bumps invalidate). 2. Dispatch `--op`: - `genome` → `loadGenome(fs, path)` or `loadCand6Genome()` + `validateGenome` - `validate` → `validateGenome(rawJson)` (raw parse so broken files reach the validator instead of throwing in the loader) - `render` → `buildSystemFromGenome(genome, ext?, glob?)` - `analyze` → `analyzeTranscript(entries)` 3. Emit one JSON object; exit 0 (or 1 under `--alert-on-invalid`, 2 on bad input). ## Examples ```bash node scripts/gepa.mjs --op genome # cand-6 + validation node scripts/gepa.mjs --op render | jq -r .system # what does cand-6 SAY? node scripts/gepa.mjs --op validate --path my-genome.json --alert-on-invalid node scripts/gepa.mjs --op analyze --transcript run.json ``` ## Exit codes - `0` — op completed (or degraded — darwin not installable) - `1` — `--alert-on-invalid` and validation found errors - `2` — config error (unknown op, missing/broken input file)

Frequently asked questions