Skip to content
Agent Orchestration
Skill

/harness-bench

Create (`bench create {repo}`) or verify (`bench verify {suite.json}`) a @metaharness/darwin bench suite, the fixed corpus `harness-evolve --bench` scores variants against. Use when preparing an evolution benchmark. Degrades gracefully without darwin.

From plugin
ruflo
80k200 skills169 agents196 commands3 MCP

Claude Code

$ npx -y skills add ruvnet/ruflo --skill harness-bench --agent claude-code

SKILL.md

harness-bench.SKILL.md
name: harness-bench
description: Create (`bench create {repo}`) or verify (`bench verify {suite.json}`) a @metaharness/darwin bench suite, the fixed corpus `harness-evolve --bench` scores variants against. Use when preparing an evolution benchmark. Degrades gracefully without darwin.
argument-hint: "--op create --repo <path> [--out <path>]  |  --op verify --suite <path>"
allowed-tools: Bash
disable-model-invocation: true

Surfaces `metaharness-darwin bench <create|verify>` — the supporting verb for `harness-evolve --bench`. Use when you want evolution scored against a fixed corpus (independent of `npm test`) so champion fitness is comparable across commits or across forks of the same harness.

When to use

  • Setting up a new evolution pipeline for a repo whose `npm test` is

flaky, slow, or undersized — scaffold a deterministic bench suite once, then evolve against it repeatedly.

  • CI: `bench verify` the checked-in suite on every PR that touches it

(cheap; ~5s).

  • Forking a harness to a new domain: copy and edit the suite to retarget

the evaluation without losing comparability to the parent.

Algorithm

Implementation: [`scripts/bench.mjs`](../../scripts/bench.mjs).

`--op create`

1. Resolve `--repo` path; reject if missing. 2. Shell to `metaharness-darwin bench create <repo> [--out <suite.json>]`. 3. Default output path: `<repo>/.metaharness/bench/suite.json` (chosen by upstream). 4. Suite shape (per upstream): array of `{ input, expectedOutput, weight }` tasks derived from existing test cases.

`--op verify`

1. Resolve `--suite` path; reject if missing. 2. Shell to `metaharness-darwin bench verify <suite.json>`. 3. Exit 1 if any task malformed (upstream's signal).

Output shape

{
  "success": true,
  "data": {
    "op": "verify",
    "taskCount": 42,
    "wellFormed": true,
    "durationMs": 870
  }
}

Exit codes

| Code | Meaning | |---|---| | 0 | OK (or degraded — Darwin absent) | | 1 | `--op verify` and suite malformed | | 2 | Config error or upstream invocation failure |

Graceful degradation

When `@metaharness/darwin` is absent, emits the standard `{degraded: true, reason: 'metaharness-darwin-not-available'}` payload and exits 0.

Read more
@ruvnet
Ships withruflo

📖 RuFlo Explained — Build an AI Team That Plans, Remembers, Tests, and Improves A 14-chapter guide: from the basic idea to a first useful task, then memory, agent teams, plugins, cost and verification. Agent = Model + Harness.

80k200 skills169 agents3 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
80.4k
Star history of ruvnet/ruflo on GitHub, a chart by star-history.com

Other skills on ruflo.

agentdb-advanced

agentdb-advanced

Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid…

@ruvnet@ruvnetInstall Skill
agentdb-learning

agentdb-learning

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer,…

@ruvnet@ruvnetInstall Skill
agentdb-memory-patterns

agentdb-memory-pattern…

Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning,…

@ruvnet@ruvnetInstall Skill
agentdb-optimization

agentdb-optimization

Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch…

@ruvnet@ruvnetInstall Skill
agentdb-vector-search

agentdb-vector-search

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware…

@ruvnet@ruvnetInstall Skill
agentic-jujutsu

agentic-jujutsu

Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

@ruvnet@ruvnetInstall Skill

More skills from other plugins.

1password

1password

Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.

clawdis2w393k
@steipete@steipeteInstall Skill
computer-use

computer-use

Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and…

orca2w111k
@stablyai@stablyaiInstall Skill
agentmail

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…

paperclip2w109k
@paperclipai@paperclipaiInstall Skill
bmad

bmad

Answers BMad questions and recommends the next skill from what is installed. Use when the user asks bmad for help, what to do…

@bmad-code-org@bmad-code-orgInstall Skill

Questions about harness-bench.

Which coding agents can use harness-bench?
harness-bench installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.