metaharness
by ruvnet
🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).
744stars
94forks
TypeScript
Added 6/29/2026
Requires a passing catalog security scan.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
AI AgentsHermes Agent Hubagent-evaluationagent-harnessagent-harness-generatoragent-scaffoldingagentic-aiagentic-frameworkautonomous-agentsclaude-codecodexcreate-agent-harnessgithub-actionshermes-agentmcpmcp-servermulti-agentopenai-codexopenclawpi-devrvmsandboxing
Maintainer of this skill?
Installation
# Add to your Claude Code skills
git clone https://github.com/ruvnet/metaharnessGetting Started
Guides for using ai agents skills like metaharness.
- Caveman: Cut Claude Token Use by 65%How agent-side prompt compression works, when to use it, and when not to.
- How to Test an AI Skill: A Practical Guide to EvalsEvaluate skills with realistic fixtures, a baseline, and repeatable checks.
- Getting Started with AI SkillsFirst-time install walkthrough for Claude Code, Codex CLI, and ChatGPT.
Security ReportIssues
Last scanned: 6/30/2026
{
"issues": [
{
"type": "npm-audit",
"message": "@vitest/mocker: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "esbuild: esbuild enables any website to send any requests to the development server and read the response",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "vite: Vite Vulnerable to Path Traversal in Optimized Deps `.map` Handling",
"severity": "high"
},
{
"type": "npm-audit",
"message": "vite-node: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "vitest: Vulnerability found",
"severity": "critical"
}
],
"status": "FAILED",
"scannedAt": "2026-06-30T07:53:31.534Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}Compare with similar skills
See how metaharness compares with popular alternatives.
MetaHarness
Mint a custom AI agent harness from any repo.
npx metaharness · open the Studio →
(Repo: ruvnet/metaharness · CLI: metaharness · Library: @ruvnet/agent-harness-generator)
Explore the full animated walkthrough → · 12 chapters · 96-second full tour · 32-second preview
Earlier 20-chapter capability tour · Open the Studio
What this is
Every serious repo deserves its own agent. A repo-aware CLI, a repo-aware coding agent, a local MCP server, memory scoped to the project, skills generated from the actual file layout, governance policy, release verification, witness-signed provenance.
metaharness mints those, on demand, from a GitHub URL or a blank slate. It is not another agent framework. It is a factory for agent frameworks.
The model is replaceable. The harness is the product.
What it gives you
In under 60 seconds, in your browser, with nothing leaving your machine:
- A custom AI agent harness for your repo (or any repo)
- Recommended agents, skills, slash commands, MCP tools
- A scoped memory namespace + governance policy
- Witness-signed provenance + release gates
- Drops into Claude Code, OpenAI Codex, pi.dev, Hermes, OpenClaw, RVM, or Prime Agent — pick one or all
Output is an npm-publishable .zip with your name on it, your branding, your npx <your-name> CLI.
New
- Bounded contrastive harness development:
@metaharness/darwin/contrastiveadds scoped proposals, actual probes, selective composition and metered experiment memory behind immutable caller policy. API guide. Independent paired confirmation adds unseen-task, statistical and regression checks. Public intent-classification evidence remains separate from general agent performance claims.
Watch Darwin evolve a harness · Explore model routing · Review experimental extensions
- Run an experimental ARC-AGI-3 harness from the ChatGPT UI.
@metaharness/arc-agi-3owns exact observations, persistent evidence-backed memory, belief-state exploration, guarded actions, supervisor interventions, checkpoints, and hash-chained receipts.@metaharness/arc-agi-3-chatgptexposes that controller as a remote MCP server and MCP Apps canvas for ChatGPT Developer Mode. ChatGPT is the OpenAI reasoning host: neither package uses the OpenAI API or anOPENAI_API_KEY. An opt-in ARC-specific AVO loop adds governed candidate selection, lineage, memory, blocking supervision, and an explicitly separate retrodiction arm. The frozen synthetic mechanism gate passes, and one actor-declared-clean single-game smoke favored AVO 3.2676 to 0.3968, but that non-competition result is not claim-eligible. All packages remain private and experimental; no ARC performance claim is made until an official closed scorecard satisfies the frozen controlled-ablation gate in ADR-254. - Governed autonomous variation for difficult engineering work.
@metaharness/avolets an agent repeatedly inspect, edit, execute real tools, evaluate, repair/revert, branch, consult structured RVF memory, and commit—while MetaHarness retains immutable capabilities, budgets, promotion, quarantine, rollback, and signed replay receipts. Simple work stays on Darwin's fast path. The runtime has a deterministic 205-action RVF interruption proof; the stronger “AVO-class” claim remains blocked on the preregistered 100-task unseen SWE-bench gate in ADR-251. ADR-276 now enforces that boundary at publication against the exact tag SHA and npm tarball, protected claim semantics, measured cost, lineage roots, and two independent graders. - Run your harness on Prime Agent — and borrow its best ideas. The 10th host
(
@metaharness/host-prime-agent,--host prime-agent) emits your tools as project-scoped, Python-backed Prime Agent skills (.prime/agent/skills/— the host has no MCP) plus an install runbook. Fail-closed: Prime Agent can't enforce a deny-list itself, so a non-empty deny-list ships a prominentSANDBOX-REQUIRED.mdinstead of silently dropping your posture. From its design we also shipped RefineMutator — an evidence-backed proposer in@metaharness/darwinthat must cite the failing traces behind each edit or propose nothing — and an opt-in--sessionscrash-recoverable JSONL session log whose Rust and TS (wasm) replays produce identical state hashes. Its PTC ("kernel as the only tool") claim is honestly deferred behind a pre-registered A/B inevals-toolcall. See ADR-246 / ADR-247. ($0) - Score any repo before you build it.
npx metaharness score <repo>reads the repo (never runs it) and prints a one-screen report card — how well a harness fits, how likely it is to build, how safe the tools are, and the rough cost per run — so you know what you'll get before scaffolding. - Pick the cheapest model that's good enough.
@metaharness/routerroutes each request to the right model from your own results — same quality, far less spend. Works out of the box with zero native deps; train it on your data for a sharper fit (npm i @metaharness/router). Add the optional@ruvector/tiny-dancerto train a fast native model instead — same training data, no API change. - Route through a learned field without replaying predecessor context.
@metaharness/field-memoryis an experimental, single-process-by-default packed-attractor layer with verified outcome caps, support quarantine, decay, cost-aware choice, and no raw-episode API. Its RuVector adapter fails closed unless a corrected flat-index wrapper is used. - Let your harness improve itself. Every scaffold now ships with Darwin Mode
(
@metaharness/darwin) wired in — runnpm run evolveand the harness mutates its own config, tests each change in a sandbox, and keeps only what measurably improves. The model stays frozen; the harness evolves. Safe by default (no network, no API key; pure refactor/tuning behind a safety gate). Validated on real SWE-bench Lite bug-fixing.--no-darwinto skip. - Opt into field memory without copying its implementation. Add
--field-memoryto scaffold a small bootstrap around the forthcoming@metaharness/field-memory@^0.1.0package. The generated harness uses packed attractors, three distinct verifier-derived principals for support, no hysteresis, and a bounded drift window. Principal independence depends on the verifier's
Frequently Asked Questions
What is metaharness?
metaharness is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by ruvnet. 🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox). It has 744 GitHub stars.
Is metaharness safe to use?
metaharness failed SkillsLLM's automated security scan, which flagged one or more high-severity issues. Review the Security Report section carefully before using it.
How do I install metaharness?
Clone the repository with "git clone https://github.com/ruvnet/metaharness" and add it to your Claude Code skills directory (see the Installation section above).
What programming language is metaharness written in?
metaharness is primarily written in TypeScript. It is open-source under ruvnet on GitHub, so you can review or fork the full source.
Are there alternatives to metaharness?
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh metaharness against similar tools.
Comments (0)
to leave a comment.
No comments yet. Be the first to share your thoughts!
Related Skills
Reverse engineer anything with agents, from app behavior down to native binaries.
451,228
111,025
TypeScript
AI Agentsagent-skillsai
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
300,993
44,412
JavaScript
AI Agentsai-agentsanthropic
Skills for Real Engineers. Straight from my .agents directory.
250,518
21,171
Shell
AI Agents
An agentic skills framework & software development methodology that works.
234,966
20,863
Shell
AI Agentsaibrainstorming