Agent skill

Create Harness

Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI.

MITAuto-check passedAgent Workflows

Install Create Harness

skills CLI

$ npx skills add ruvnet/metaharness --skill create-harness -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install ruvnet/metaharness create-harness --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/ruvnet/metaharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude-plugin/skills/create-harness .claude/skills/create-harness && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "create-harness" agent skill from https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/create-harness into .claude/skills/create-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-harness", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/create-harness

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add ruvnet/metaharness --skill create-harness -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install ruvnet/metaharness create-harness --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ruvnet/metaharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude-plugin/skills/create-harness .agents/skills/create-harness && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "create-harness" agent skill from https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/create-harness into .agents/skills/create-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-harness", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ruvnet/metaharness --skill create-harness -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install ruvnet/metaharness create-harness --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ruvnet/metaharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude-plugin/skills/create-harness .cursor/skills/create-harness && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "create-harness" agent skill from https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/create-harness into .cursor/skills/create-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-harness", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/ruvnet/metaharness.git --path .claude-plugin/skills/create-harness

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add ruvnet/metaharness --skill create-harness -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install ruvnet/metaharness create-harness --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ruvnet/metaharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude-plugin/skills/create-harness .gemini/skills/create-harness && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "create-harness" agent skill from https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/create-harness into .gemini/skills/create-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-harness", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install ruvnet/metaharness create-harness

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add ruvnet/metaharness --skill create-harness -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/ruvnet/metaharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude-plugin/skills/create-harness .github/skills/create-harness && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "create-harness" agent skill from https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/create-harness into .github/skills/create-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-harness", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ruvnet/metaharness --skill create-harness -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install ruvnet/metaharness create-harness --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ruvnet/metaharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude-plugin/skills/create-harness .opencode/skills/create-harness && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "create-harness" agent skill from https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/create-harness into .opencode/skills/create-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-harness", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: create-harness
GitHub stars: 688
Token cost: ~777 tokens
SKILL.md length: 325 words
Files: 1
Skills in repo: 14
Repo updated: Oct 6, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI.

Works in 7 steps: Harness name (kebab-case, e.g.… → Description (one line) → Host(s) — Claude Code, Codex, pi.dev,… → …
A user asks to create my own agent harness
SKILL.md covers When to use this skill, How to invoke, Under the hood and Outputs, plus 2 more sections
Calls npm and npx

What it does

Create Harness is an agent skill from ruvnet/metaharness. Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a vertical AI assistant for X".

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Project scaffolding and Hooks and plugins. It works with npm and Model Context Protocol. The repository describes itself as: 🛠️ 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… The licence is MIT.

When your agent uses it

A user asks to create my own agent harness
Scaffold a harness
Make a custom Claude Code plugin like ruflo
Build a vertical AI assistant for X

Example prompts

“create my own agent harness”
“scaffold a harness”
“make a custom Claude Code plugin like ruflo”
“/create-harness”

Requirements

Node.js

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

Harness name (kebab-case, e.g. legal-redline)
Description (one line)
Host(s) — Claude Code, Codex, pi.dev, Hermes (multi-select)
Template — minimal (default), vertical:trading, vertical:support, vertical:devops, vertical:legal, vertical:research, or eject-from-ruflo
Memory backend — AgentDB (default), SQLite-only, in-memory
Routing strategy — 3-tier (default) or single-tier
Marketplace — independent (no ruflo branding) or powered-by

What it can do on your machine

Read from SKILL.md and the folder at commit 53a251d. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- npm
- npx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm and npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Create Harness loads about 777 tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 325 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~89
When it runs · the whole SKILL.md, loaded when a task matches: ~777

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ruvnet/metaharness at commit 53a251d, republished under its MIT licence (© ruvnet). 325 words, ~777 tokens.

Download SKILL.mdSave it as .claude/skills/create-harness/SKILL.md (or your agent's skills folder).

name: create-harness
description: Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a vertical AI assistant for X".

create-harness

This skill scaffolds an AI agent harness — your own focused, branded harness with its own npx <name> CLI, MCP server registration, memory namespace, learning loop, and marketplace identity.

When to use this skill

Use this skill when the user wants any of:

A custom MCP-server-backed AI assistant (legal, trading, support, ops, …)
A Claude Code plugin that bundles their own agents/skills/prompts
A Codex skill that wraps a kernel + tools
A pi.dev extension or Hermes agent runtime config
A standalone npm package they can npm publish under their own scope

How to invoke

/create-harness

The skill asks for:

Harness name (kebab-case, e.g. legal-redline)
Description (one line)
Host(s) — Claude Code, Codex, pi.dev, Hermes (multi-select)
Template — minimal (default), vertical:trading, vertical:support, vertical:devops, vertical:legal, vertical:research, or eject-from-ruflo
Memory backend — AgentDB (default), SQLite-only, in-memory
Routing strategy — 3-tier (default) or single-tier
Marketplace — independent (no ruflo branding) or powered-by

Under the hood

Calls npx create-agent-harness <name> with the user's choices, copies the chosen template into the current directory, runs the post-generation smoke test, and emits a .harness/manifest.json so future updates can harness upgrade cleanly (copier-style regenerate-diff-merge).

Outputs

File	Purpose
`package.json`	The harness's npm package, ready to `npm publish`
`bin/<name>.js`	The CLI binary your users invoke
`.claude/settings.json` (if Claude Code host)	MCP + hooks wiring
`.codex/config.toml` (if Codex host)	MCP table in TOML
`AGENTS.md` + `SYSTEM.md` (if pi.dev host)	Pi extension instructions
`cli-config.yaml` (if Hermes host)	Hermes runtime config
`.harness/manifest.json`	Generator state — drives drift detection (ADR-008)
`witness.json`	Ed25519-signed provenance manifest (ADR-011)

After scaffolding

The user can:

bash

cd <name>
npm install
npm test
npm publish              # ship their harness to npm
# their users: npx <name> init

Notes for the model

This is a deterministic operation — defer to create-agent-harness for the actual file creation, do NOT generate harness file contents yourself
The witness manifest is required — do not skip it
If the user asks for "ruflo for X" or "my own ruflo", recommend vertical:<X> templates first and offer minimal as the fallback
Multi-host is supported but increases the harness's surface area — recommend single-host for first-time users unless they explicitly need multi-host

Files

Just SKILL.md in .claude-plugin/skills/create-harness of ruvnet/metaharness.

Open the folder on GitHubat commit 53a251d

Compare with similar skills

Create Harness next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Create Harness compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Create Harness this skillruvnet/metaharness	688	—	~777	Automated safety check: Pass	MIT	today
Writing Pluginsnukeop/nuclear	19k	—	~825	Automated safety check: Pass	AGPL-3.0	yesterday
OpenCode Plugin CreatorDevin-AXIS/iPolloWork	6.7k	1 repos	~1.3k	Automated safety check: Pass	Custom licence	today
Paseo Plugin Buildergetpaseo/paseo	20k	—	~9.4k	Automated safety check: Pass	Custom licence	today
Tsed CLItsedio/tsed	3.1k	—	~2.7k	Automated safety check: Pass	MIT	2 days ago
Context Mode Doctormksglu/context-mode	26k	—	~262	Automated safety check: Pass	Custom licence	today

Similar skills

Writing Plugins
nukeop/nuclear
A skill your agent uses when writing, scaffolding, or modifying Nuclear plugins.
19k GitHub stars~825 tokensUpdated yesterday
Agent WorkflowsAuto-check passed
OpenCode Plugin Creator
Devin-AXIS/iPolloWork
Scaffolds an OpenCode plugin for iPolloWork with the right async factory shape, zod-based tool definitions and hook registration, and explains where to place and register it.
6.7k GitHub starsUsed in 1 repo~1.3k tokens
Agent WorkflowsAuto-check passed
Paseo Plugin Builder
getpaseo/paseo
Builds, installs and troubleshoots trusted local Paseo plugins, from lifecycle hooks and slash commands to screens, themes and timeline renderers.
20k GitHub stars~9.4k tokensUpdated today
Agent WorkflowsAuto-check passed
Tsed CLI
tsedio/tsed
Scaffolds Ts.ED v8 projects and generates files with the Ts.ED CLI v7, through its MCP server (tools set-workspace, init-project, list-templates, get-template, generate-file) or the tsed binary…
3.1k GitHub stars~2.7k tokensUpdated 2 days ago
DevelopmentAuto-check passed
Context Mode Doctor
mksglu/context-mode
Run context-mode diagnostics. Checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. Trigger: /context-mode:ctx-doctor
26k GitHub stars~262 tokensUpdated today
Agent WorkflowsAuto-check passed
Context Mode Upgrade
mksglu/context-mode
Update context-mode from GitHub and fix hooks/settings. Pulls latest, builds, installs, updates npm global, configures hooks. Trigger: /context-mode:ctx-upgrade
26k GitHub stars~291 tokensUpdated today
Agent WorkflowsAuto-check passed

Questions about Create Harness

What does Create Harness do?

Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Create Harness is an agent skill from ruvnet/metaharness.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI.

When should I use Create Harness?

Create Harness fits situations like: A user asks to create my own agent harness; scaffold a harness; make a custom Claude Code plugin like ruflo; build a vertical AI assistant for X.

How do I install Create Harness in Claude Code?

Run `npx skills add ruvnet/metaharness --skill create-harness -a claude-code`. Or copy the skill folder (.claude-plugin/skills/create-harness in ruvnet/metaharness) into .claude/skills/create-harness in your project. Claude Code loads it when a task matches its description.

How do I install Create Harness in Codex?

Run `npx skills add ruvnet/metaharness --skill create-harness -a codex`. Or copy the skill folder (.claude-plugin/skills/create-harness in ruvnet/metaharness) into .agents/skills/create-harness in your project. Codex loads it when a task matches its description.

Can I use Create Harness in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ruvnet/metaharness --skill create-harness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-harness, .gemini/skills/create-harness, .github/skills/create-harness and .opencode/skills/create-harness in your project.

What does Create Harness need to run?

Going by SKILL.md and its folder, Create Harness needs the command-line tools its instructions call (npm and npx). Our summary lists: Node.js.

Does Create Harness access the network?

SKILL.md contains no URLs. Its commands use npm and npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Create Harness safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Create Harness use?

Create Harness is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Create Harness use?

About 777 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Create Harness?

Skills that share tags, products or a category with Create Harness: Writing Plugins (nukeop/nuclear, 19k stars), OpenCode Plugin Creator (Devin-AXIS/iPolloWork, 6.7k stars), Paseo Plugin Builder (getpaseo/paseo, 20k stars) and Tsed CLI (tsedio/tsed, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create Harness?

ruvnet (a GitHub user) maintains it in ruvnet/metaharness, which has 688 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 6, 2026.

Source: ruvnet/metaharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Create Harness

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

create-harness

When to use this skill

How to invoke

Under the hood

Outputs

After scaffolding

Notes for the model

Files

Compare with similar skills

Similar skills

More from ruvnet/metaharness

Related

Questions about Create Harness