Agent skill

Compare Harnesses

Diff two scaffolded harnesses (ADR-031). An agent skill from ruvnet/metaharness.

MITAuto-check passedDevelopment

Install Compare Harnesses

skills CLI

$ npx skills add ruvnet/metaharness --skill compare-harnesses -a claude-code

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

GitHub CLI

$ gh skill install ruvnet/metaharness compare-harnesses --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/compare-harnesses .claude/skills/compare-harnesses && 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 "compare-harnesses" agent skill from https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/compare-harnesses into .claude/skills/compare-harnesses/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compare-harnesses", 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/compare-harnesses

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 compare-harnesses -a codex

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

GitHub CLI

$ gh skill install ruvnet/metaharness compare-harnesses --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/compare-harnesses .agents/skills/compare-harnesses && 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 "compare-harnesses" agent skill from https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/compare-harnesses into .agents/skills/compare-harnesses/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compare-harnesses", 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 compare-harnesses -a cursor

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

GitHub CLI

$ gh skill install ruvnet/metaharness compare-harnesses --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/compare-harnesses .cursor/skills/compare-harnesses && 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 "compare-harnesses" agent skill from https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/compare-harnesses into .cursor/skills/compare-harnesses/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compare-harnesses", 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/compare-harnesses

--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 compare-harnesses -a gemini-cli

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

GitHub CLI

$ gh skill install ruvnet/metaharness compare-harnesses --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/compare-harnesses .gemini/skills/compare-harnesses && 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 "compare-harnesses" agent skill from https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/compare-harnesses into .gemini/skills/compare-harnesses/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compare-harnesses", 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 compare-harnesses

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 compare-harnesses -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/compare-harnesses .github/skills/compare-harnesses && 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 "compare-harnesses" agent skill from https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/compare-harnesses into .github/skills/compare-harnesses/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compare-harnesses", 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 compare-harnesses -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 compare-harnesses --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/compare-harnesses .opencode/skills/compare-harnesses && 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 "compare-harnesses" agent skill from https://github.com/ruvnet/metaharness/tree/main/.claude-plugin/skills/compare-harnesses into .opencode/skills/compare-harnesses/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compare-harnesses", 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: compare-harnesses
GitHub stars: 694
Token cost: ~1k tokens
SKILL.md length: 333 words
Files: 1
Skills in repo: 14
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Diff two scaffolded harnesses (ADR-031). An agent skill from ruvnet/metaharness.

Works in 3 steps: Manifest meta — same name? same kernel?… → Hosts — which host adapters each side… → Files — added / removed / changed…
Tasks that involve Project scaffolding
SKILL.md covers What it does, Usage from Codex, Equivalent CLI and Sample output (text mode), plus 3 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Compare Harnesses is an agent skill from ruvnet/metaharness. Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.

Its SKILL.md is about 1k 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 Development, covering Project scaffolding and Architecture decision records. It works with 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

Tasks that involve Project scaffolding
Tasks that involve Architecture decision records

Example prompts

“/compare-harnesses”

Workflow steps

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

Manifest meta — same name? same kernel? same surface?
Hosts — which host adapters each side ships (claude-code /
Files — added / removed / changed (per-file SHA-256 fingerprints;

What it can do on your machine

Read from SKILL.md and the folder at commit ea287d6. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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

Compare Harnesses loads about 1k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 333 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~64
When it runs · the whole SKILL.md, loaded when a task matches: ~1k

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 ea287d6, republished under its MIT licence (© ruvnet). 333 words, ~1,023 tokens.

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

name: compare-harnesses
description: Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.

compare-harnesses

Codex skill: diff two scaffolded harnesses — the ADR-031 Bundle JSON Pattern surfaced through Codex (iter 105 → iter 109).

What it does

Two-harness diff. Useful when you've forked an upstream template, when a support ticket says "mine and theirs scaffolded different things", or when a CI script wants a byte-equality check between a candidate scaffold and a known-good baseline.

Reports three sections:

Manifest meta — same name? same kernel? same surface?
Hosts — which host adapters each side ships (claude-code / codex / pi-dev / hermes / openclaw / rvm)
Files — added / removed / changed (per-file SHA-256 fingerprints; the cheapest possible byte-equality test)

Verdict	Exit	Meaning
`IDENTICAL`	0	meta + hosts + every file fingerprint matches
`DRIFT`	1	at least one of meta / hosts / files differs
`no-manifest-in-a`	2	`a/.harness/manifest.json` missing
`no-manifest-in-b`	2	`b/.harness/manifest.json` missing
`no-manifest-in-either`	2	both sides missing manifest

Usage from Codex

/compare-harnesses a=./my-fork b=./upstream
/compare-harnesses a=./my-fork b=./upstream bundle=true

Equivalent CLI

bash

harness compare ./my-fork ./upstream                  # text output
harness compare ./my-fork ./upstream --bundle         # ADR-031 schema-1 JSON

The --bundle form (ADR-031) emits a schema-1 JSON envelope so CI scripts can json-parse the verdict without re-parsing human text. The envelope shape is shared with harness diag --bundle, harness export-config, and harness audit --bundle:

json

{
  "schema": 1,
  "generatedAt": "2026-06-15T...",
  "a": "/path/to/a",
  "b": "/path/to/b",
  "meta": { "sameKernel": true, "sameSurface": true, "sameName": false },
  "hosts": { "a": ["claude-code"], "b": ["claude-code", "codex"], "verdict": "PASS" | "FAIL" },
  "files": { "added": [...], "removed": [...], "changed": [...] },
  "identical": false,
  "exitCode": 1
}

Errors are bundle-formed too ({ "schema": 1, "error": "no-manifest-in-a" }), so a CI script never has to dual-parse text + JSON. Object keys matching secret|token|key|password|passphrase are redacted via the canonical ADR-031 sanitisation regex before emission — safe to paste into a public GitHub issue.

Sample output (text mode)

harness compare — diffing /tmp/a /tmp/b

  name:              A=cmp-a   B=cmp-b   FAIL
  kernel:            A=0.1.0   B=0.1.0   PASS
  surface:           A=cli     B=cli     PASS
  hosts:             A=[claude-code] B=[claude-code,codex] FAIL

  added:             3 files
    + src/agents/codex-tester.ts
    + src/agents/codex-reviewer.ts
    + .codex/config.toml
  removed:           0 files
  changed:           1 file
    ~ .harness/manifest.json

DRIFT (exit 1)

When to use it

You forked the project's upstream template, edited it, and want to know exactly what diverged before sending a PR upstream.
A user files a "this doesn't work" bug; you run harness compare their-zip yours-zip --bundle > diff.json and attach the bundle to the issue.
CI is the canonical place: a nightly job runs compare between today's scaffold output and a frozen baseline, fails the run on DRIFT.

diag-harness — single-harness kernel-version skew check (iter 66)
validate-harness — release-readiness umbrella (iter 20)
verify-witness — Ed25519 witness signature verification (iter 8)

Files

Just SKILL.md in .claude-plugin/skills/compare-harnesses of ruvnet/metaharness.

Open the folder on GitHubat commit ea287d6

Compare with similar skills

Compare Harnesses 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.

Compare Harnesses compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Compare Harnesses this skillruvnet/metaharness	694	—	~1k	Automated safety check: Pass	MIT	today
Run Nx Generatornrwl/nx	29k	2 repos	~592	Automated safety check: Notes	MIT	today
Tsed CLItsedio/tsed	3.1k	—	~2.7k	Automated safety check: Pass	MIT	yesterday
Trellis Spec Bootstarpanjiemo/SunnyBeach	178	7 repos	~740	Automated safety check: Pass	Apache-2.0	28 days ago
Task Workflowikarenkov/Modo	343	—	~2.4k	Automated safety check: Pass	None	3 mo ago
Cabloy Spec Generationcabloy/cabloy	982	—	~3.2k	Automated safety check: Notes	MIT	today

Similar skills

Run Nx Generator
nrwl/nx
Run Nx generators with prioritization for workspace-plugin generators.
29k GitHub starsUsed in 2 repos~592 tokens
DevelopmentAuto-check: notes
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 yesterday
DevelopmentAuto-check passed
Trellis Spec Bootstarp
anjiemo/SunnyBeach
Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow.
178 GitHub starsUsed in 7 repos~740 tokens
DevelopmentAuto-check passed
Task Workflow
ikarenkov/Modo
Spec-driven workflow for non-trivial work. An agent skill from ikarenkov/Modo.
343 GitHub stars~2.4k tokensUpdated 3 mo ago
DevelopmentAuto-check passed
Cabloy Spec Generation
cabloy/cabloy
A skill your agent uses to create or maintain Cabloy suite specifications under repo-specs, including PRD, SRS, PDP/WBS, acceptance planning, progress, and suite ADRs.
982 GitHub stars~3.2k tokensUpdated today
DevelopmentAuto-check: notes
Better Fullstack
Marve10s/Better-Fullstack
Scaffold, plan, or extend Better Fullstack projects with the generator, CLI, or MCP server.
754 GitHub stars~1.5k tokensUpdated yesterday
DevelopmentAuto-check passed

Questions about Compare Harnesses

What does Compare Harnesses do?

Diff two scaffolded harnesses (ADR-031). An agent skill from ruvnet/metaharness. Compare Harnesses is an agent skill from ruvnet/metaharness. Diff two scaffolded harnesses (ADR-031).

When should I use Compare Harnesses?

Compare Harnesses fits situations like: tasks that involve Project scaffolding; tasks that involve Architecture decision records.

How do I install Compare Harnesses in Claude Code?

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

How do I install Compare Harnesses in Codex?

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

Can I use Compare Harnesses 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 compare-harnesses -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/compare-harnesses, .gemini/skills/compare-harnesses, .github/skills/compare-harnesses and .opencode/skills/compare-harnesses in your project.

What does Compare Harnesses need to run?

SKILL.md names no scripts, command-line tools or credentials: Compare Harnesses is instructions for the agent only.

Does Compare Harnesses access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Compare Harnesses 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 Compare Harnesses use?

Compare Harnesses 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 Compare Harnesses use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Compare Harnesses?

Skills that share tags, products or a category with Compare Harnesses: Run Nx Generator (nrwl/nx, 29k stars), Tsed CLI (tsedio/tsed, 3.1k stars), Trellis Spec Bootstarp (anjiemo/SunnyBeach, 178 stars) and Task Workflow (ikarenkov/Modo, 343 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Compare Harnesses?

ruvnet (a GitHub user) maintains it in ruvnet/metaharness, which has 694 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 9, 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.

Compare Harnesses

Install Compare Harnesses

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

compare-harnesses

What it does

Usage from Codex

Equivalent CLI

Sample output (text mode)

When to use it

See also

Files

Compare with similar skills

Similar skills

Run Nx Generator

Tsed CLI

Trellis Spec Bootstarp

Task Workflow

Cabloy Spec Generation

Better Fullstack

More from ruvnet/metaharness

Create Harness

Diag Harness

Example Harness

Oia Manifest

Repo Genome

Score Harness

Questions about Compare Harnesses

Install Compare Harnesses

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

compare-harnesses

What it does

Usage from Codex

Equivalent CLI

Sample output (text mode)

When to use it

Related skills

See also

Files

Compare with similar skills

Similar skills

More from ruvnet/metaharness

Related

Questions about Compare Harnesses