ruvnet

MetaHarness × GitHub Actions

A one-command scaffold for a non-interactive AI agent harness that runs on the GitHub Actions runner — the 9th MetaHarness host (ADR-033) and the only one built for CI/CD.

Intro

Every other MetaHarness host is interactive: a human starts a session and watches the agent work. GitHub Actions is different in kind. There's no human at the keyboard — execution is triggered by a webhook (a push, a pull request, an issue comment, or a schedule), the "operator" is the runner, and the harness must complete its task autonomously, emit structured output, and exit cleanly.

@metaharness/github-actions is a thin wrapper around the metaharness CLI. Running it is equivalent to npx metaharness my-bot --template minimal --host github-actions.

ruvnet

MetaHarness: trading vertical

Intro

@metaharness/trading is a one-shot scaffold that drops a complete, opinionated quantitative-trading workspace onto your machine, ready to drive from Claude Code. It is built on top of metaharness — the generic harness generator — and pre-fills the trading-shaped pieces: a research-to-execution agent pipeline, a non-bypassable risk gate, paper-trading defaults, and a stub broker so you can run end-to-end without ever touching real capital.

It is intended for quants prototyping signals, algo-trading hobbyists who want a serious starting point instead of a notebook, and trading-platform integrators who want a sane reference layout. It is not a turnkey live-trading bot. There are no broker credentials, no live market-data subscription, and no production order router included. You bring those when you're ready.

Usage details

ruvnet

Intro

@metaharness/support is a one-command scaffold that drops a complete customer-support multi-agent template into a fresh directory, wired for Claude Code. You run npx @metaharness/support@latest my-bot, and you get a working four-agent pipeline — triager, KB-searcher, responder, escalator — plus the MCP servers, permissions, and pipeline contract that make those agents cooperate instead of stepping on each other.

It is a template, not a product. There is no hosted dashboard, no vendor lock-in, no SaaS account. The scaffold gives you files on disk that you own, edit, and version-control. Bring your own knowledge base, ticketing backend, and escalation channel.

Usage details

The minimum workflow:

ruvnet

Intro

@metaharness/sales is a one-command scaffold that drops a working three-agent sales pipeline into a fresh directory, wired up for Claude Code. It gives you a qualifier (lead scoring against your ICP), an opener (first-touch outreach with personalized variants), and a closer (objection handling and multi-thread follow-up) — all coordinated through shared memory and dispatched to the right tier of model so you are not paying Opus prices to score a cold lead.

This is the kind of thing you'd otherwise spend an afternoon stubbing out: agent prompts, MCP server wiring, hook configuration, model routing rules, a doctor command to tell you what is broken. The scaffold ships all of it in seconds and leaves clean files you own and can edit.

It is not a CRM. It does not send real email. It does not include leads. You bring the pipeline data and the outbound transport; the scaffold brings the agent choreography.

Usage details

ruvnet

MetaHarness × RVM deployment-target partition

Intro

@metaharness/rvm is a one-shot scaffolder for a minimal agent harness pre-configured against the RVM deployment-target partition. If you have spent time wiring up an agent harness by hand — picking a settings.json shape, deciding where agents/ lives, registering MCP servers, figuring out which paths are host-specific vs. portable — this skips that. You get a clean directory you can read in two minutes, a working harness doctor pass, and the right defaults for the RVM host partition. It is deliberately minimal: no example crew, no pre-built workflow, no opinions about what your agent does. Just the harness shape, done right.

This is a host package in the metaharness ecosystem — it integrates the harness with a specific deployment target (RVM). It is not a vertical template (those ship a ready-made multi-agent crew for a specific use case like research or code review). If you want a crew, layer one on top after scaffolding, or pick a verti

ruvnet

Intro

@metaharness/research is a one-command scaffold that drops a working, six-agent research pipeline into a fresh project, wired for Claude Code. You give it a topic, the harness fans out web searches across sub-queries, grades the sources it finds, synthesizes a cited report, and then adversarially fact-checks every claim against its source before handing you the markdown. It is for people who already have Claude Code installed and want a real multi-agent template instead of yet another single-prompt "research GPT" demo.

What it is not: a hosted service, a search API, or a UI. It is the prompts, agent definitions, slash command, and .claude/settings.json you would otherwise spend a weekend writing yourself — generated by the underlying metaharness CLI and pinned to a known-good vertical template.

Usage details

ruvnet

Intro

@metaharness/repo-maintainer is a one-command scaffold for an open-source repo maintenance bot that runs on top of Claude Code. Instead of stitching together agents, prompts, MCP servers, and permission allowlists yourself, you run a single npx command and get a folder with three coordinated agents — a triager, a reviewer, and a release manager — already wired to the GitHub MCP server, the gh CLI, and the lint/test commands declared in a config file.

It's aimed at maintainers who already use Claude Code and want an opinionated starting point for offloading the high-volume, low-judgement parts of running a repo: labeling issues, asking for missing repros, dedup-ing against the existing backlog, running the test suite on a PR diff, leaving inline review comments, drafting a changelog from merged PRs, and opening a release PR. It deliberately does not auto-merge, force-push, or open release tags without your acceptance — the default permission mode requires acceptEdits for anything beyond rea

ruvnet

@metaharness/pi-dev — pi.dev AGENTS.md harness in one command

Intro

@metaharness/pi-dev is a one-shot scaffolding package for the pi.dev agent runtime. It uses the metaharness generator under the hood to drop a clean, minimal, ready-to-commit project layout that pi.dev workers can immediately pick up. The scaffold gives you the canonical AGENTS.md contract that AGENTS.md-aware hosts read on startup, plus a pi.dev-specific host config, an empty-but-valid MCP server registry, and a single starter agent you can rename or fork.

It is deliberately minimal. It does not bake in a multi-agent topology, a domain vertical (healthcare, finance, etc.), or an evaluation harness. If you want any of those, pick a vertical metaharness package instead. If you want a clean working directory you can iterate on, you're in the right place.

Usage details

ruvnet

Intro

@metaharness/opencode is a one-command scaffold that gives you a working OpenCode .opencode/ configuration tree wired into the MetaHarness CLI. MetaHarness is the underlying agent-harness generator (see https://github.com/ruvnet/agent-harness-generator); this package is a thin, pinned wrapper that hard-codes the right template and host flags so you don't have to remember them.

The goal is simple: if you want to start an OpenCode-based agent project and you are tired of copying boilerplate from another repo, run one npx command and you have a clean skeleton in seconds. It is deliberately minimal — no example agents, no preloaded MCP servers, no opinionated prompts. It gets out of your way.

Usage details

Run the scaffold:

ruvnet

Intro

@metaharness/openclaw is a one-shot scaffolder that drops a working OpenClaw-compatible project on disk in about two seconds. OpenClaw is an open-source AI coding host that reads its configuration from a .openclaw/ directory in your project root — and writing that directory from scratch every time you start a new bot is annoying, error-prone, and easy to copy-paste wrong from someone else's repo. This package solves the bootstrapping step. You run one npx command, you get a folder, the folder is laid out the way OpenClaw expects, and you can start editing agents instead of debugging config schemas.

The package is part of the MetaHarness family of example scaffolds. MetaHarness is the underlying generator; @metaharness/openclaw is a thin wrapper that pre-selects the minimal template and the openclaw host so you don't have to remember the flags. It does NOT install the OpenClaw runtime, ship a language model, or