harness-learn
Run a GEPA learning cycle via `metaharness learn` (upstream ADR-235, metaharness@0.3.0) — optimizes a harness genome against a SWE-bench-style slice manifest. $0 dry-run by default; `--run` is the explicit spend opt-in. Requires a metaharness repo checkout (`--repo` or $METAHARNESS_REPO) — without one it reports `checkout-required` with clone instructions. Degrades gracefully when metaharness is absent.
Profile →npx skills add ruvnet/ruflo --skill harness-learn --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
Surfaces `metaharness learn` — the upstream GEPA learning harness that evolves harness policy genomes against a scored task corpus instead of hand-editing prompts. Candidates are scored on held-out slices and only measured winners promote (the shipped cand-6 genome is the first such promotion: holdout gold 2/12 → 3/12, zero regressions). ## When to use - A harness's policy prompt underperforms on a task family and you want a measured improvement loop rather than manual prompt iteration. - Pricing a learning run before committing spend — the default dry-run resolves the slice manifest and reports cost without any model calls. - After a learn run promotes a genome: pair with `harness-gepa --op render` to inspect what the promoted policy actually says. ## Preconditions (upstream design) The learning harness (GEPA + SWE-bench + Docker) is too heavy for the npm package, so `learn` needs a local clone: ```bash git clone https://github.com/ruvnet/metaharness.git node scripts/learn.mjs --repo ./metaharness --host claude-code --model haiku --slice slices/lite.json ``` Without a checkout the script emits `{status: "checkout-required"}` and exits 0 — a precondition report, not an error (disti
- When to use
- Preconditions (upstream design)
- Algorithm
- Cost note
- Exit codes
git clone https://github.com/ruvnet/metaharness.git node scripts/learn.mjs --repo ./metaharness --host claude-code --model haiku --slice slices/lite.json
What does the harness-learn skill do?
Run a GEPA learning cycle via `metaharness learn` (upstream ADR-235, metaharness@0.3.0) — optimizes a harness genome against a SWE-bench-style slice manifest. $0 dry-run by default; `--run` is the explicit spend opt-in. Requires a metaharness repo checkout (`--repo` or $METAHARNESS_REPO) — without one it reports `checkout-required` with clone instructions. Degrades gracefully when metaharness is absent.
How do I install it?
Run `npx skills add ruvnet/ruflo --skill harness-learn --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ruvnet/ruflo, a repository with 67,015 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.