Agent skill

Verify Witness

by ruvnet in ruvnet/metaharness

Verify the Ed25519 witness manifest of a scaffolded harness.

MITAuto-check passedProduct & Project Management

Install Verify Witness

skills CLI
$ npx skills add ruvnet/metaharness --skill verify-witness -a claude-code

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

GitHub CLI
$ gh skill install ruvnet/metaharness verify-witness --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/verify-witness .claude/skills/verify-witness && 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/

Facts

Skill name
verify-witness
GitHub stars
696
Token cost
~472 tokens
SKILL.md length
184 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Verify the Ed25519 witness manifest of a scaffolded harness.

  • Tasks that involve Project scaffolding
  • SKILL.md covers What it does, Usage from Codex, Equivalent CLI and Why it's separate from…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Feature launches and release readiness

What it does

Verify Witness is an agent skill from ruvnet/metaharness. Verify the Ed25519 witness manifest of a scaffolded harness. Fast yes/no signature check that proves the publisher signed this exact file set — separate from the full release-readiness umbrella in validate-harness.

Its SKILL.md is about 470 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 Product & Project Management, covering Project scaffolding and Feature launches and release readiness. 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 Feature launches and release readiness

Example prompts

  • “/verify-witness”

What it can do on your machine

Read from SKILL.md and the folder at commit e0dfd44. 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).

    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

Verify Witness loads about 472 tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 184 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~472

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 e0dfd44, republished under its MIT licence (© ruvnet). 184 words, ~472 tokens.

Download SKILL.mdSave it as .claude/skills/verify-witness/SKILL.md (or your agent's skills folder).
name
verify-witness
description
Verify the Ed25519 witness manifest of a scaffolded harness. Fast yes/no signature check that proves the publisher signed this exact file set — separate from the full release-readiness umbrella in validate-harness.

verify-witness

Codex skill: Ed25519 witness manifest verification for a scaffolded harness.

What it does

Reads .harness/witness.json, validates the Ed25519 signature against the embedded public key, and reports VALID / INVALID with a one-line reason.

Distinct from validate-harness:

  • validate-harness is the umbrella — doctor + verify + path-guard + mcp + secrets
  • verify-witness is only the signature check — fast yes/no for CI / federation handshakes / multi-signer workflows

Usage from Codex

/verify-witness
/verify-witness path=./my-harness
/verify-witness path=./my-harness strict=false

Equivalent CLI

bash
harness verify ./my-harness

Why it's separate from validate-harness

When two harnesses federate (iter 9), they need to confirm each other's witness signatures BEFORE doing the full release-readiness check. Splitting this surface lets federation peers run a fast signature handshake without paying for the full validate sweep.

Also: CI workflows that only care about signature integrity (e.g. mirroring a published harness to a private registry) can call this skill instead of the heavier umbrella.

What's checked

CheckDetail
File present.harness/witness.json exists
Manifest shapeAll required fields (harness, version, entries, public_key, signature)
SignatureEd25519 verify against the embedded public key
Strict modeIf strict=true and no witness, exit non-zero. If false, soft-skip with PASS

Exit 0 = signature VALID. Exit 1 = INVALID / missing (strict mode).

© ruvnet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude-plugin/skills/verify-witness of ruvnet/metaharness.

Open the folder on GitHubat commit e0dfd44

Compare with similar skills

Verify Witness 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.

Verify Witness compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Verify Witness this skillruvnet/metaharness696—~472Automated safety check: PassMIT
Azsdk Common Prepare Release PlanAzure/azure-sdk-for-android121—~733Automated safety check: PassMIT
Azsdk Common Prepare Release PlanAzure/azure-sdk-tools134—~2.7kAutomated safety check: PassMIT
Roam Release ReadinessCranot/roam-code517—~1.7kAutomated safety check: PassApache-2.0
Run Nx Generatornrwl/nx29k2 repos~592Automated safety check: NotesMIT
AI Project Copilotsun461941-hub/ai-project-copilot97—~3kAutomated safety check: PassMIT

Similar skills

  • Azsdk Common Prepare Release Plan

    Azure/azure-sdk-for-android

    Official

    Create and manage release plan work items for Azure SDK releases across languages.

    121 GitHub stars~733 tokensUpdated 4 mo ago
    Product & Project ManagementAuto-check passed
  • Official

    Create, get, update, abandon, and link SDK PRs to release plan work items for Azure SDK releases.

    134 GitHub stars~2.7k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Roam Release Readiness

    Cranot/roam-code

    Qualify a Roam commit or accumulated batch for package, website, or server publication; reconcile source, tests, review, CI and deployed identities, and identify the next authorized release step.

    517 GitHub stars~1.7k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Run Nx generators with prioritization for workspace-plugin generators.

    29k GitHub starsUsed in 2 repos~592 tokens
    DevelopmentAuto-check: notes
  • AI Project Copilot

    sun461941-hub/ai-project-copilot

    A skill your agent uses to turn an AI idea or existing repository into a credible open-source product and to run evidence-first repository engineering across codebase discovery, context-efficient…

    97 GitHub stars~3k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Pre Release Test

    herald-email/herald-mail-app

    A skill your agent uses when preparing a Herald beta release, checking release readiness, or running broad deterministic integration gates across TUI themes, inline images, SSH, and MCP before…

    146 GitHub stars~448 tokensUpdated 3 mo ago
    Product & Project ManagementAuto-check passed

More from ruvnet/metaharness

All 14 skills in this repo
  • Create Harness

    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.

    696 GitHub stars~777 tokensUpdated yesterday
    Auto-check passed
  • Compare Harnesses

    ruvnet/metaharness

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

    696 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • Diag Harness

    ruvnet/metaharness

    Kernel-version skew check (ADR-027). An agent skill from ruvnet/metaharness.

    696 GitHub stars~835 tokensUpdated yesterday
    Auto-check passed
  • Example Harness

    ruvnet/metaharness

    Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot…

    696 GitHub stars~735 tokensUpdated yesterday
    Auto-check passed
  • Oia Manifest

    ruvnet/metaharness

    Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture.

    696 GitHub stars~910 tokensUpdated yesterday
    Auto-check passed
  • Repo Genome

    ruvnet/metaharness

    7-section readiness scorecard for a LOCAL repo. An agent skill from ruvnet/metaharness.

    696 GitHub stars~772 tokensUpdated yesterday
    Auto-check passed

Questions about Verify Witness

What does Verify Witness do?

Verify the Ed25519 witness manifest of a scaffolded harness. Verify Witness is an agent skill from ruvnet/metaharness. Verify the Ed25519 witness manifest of a scaffolded harness.

When should I use Verify Witness?

Verify Witness fits situations like: tasks that involve Project scaffolding; tasks that involve Feature launches and release readiness.

How do I install Verify Witness in Claude Code?

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

How do I install Verify Witness in Codex?

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

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

What does Verify Witness need to run?

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

Does Verify Witness 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 Verify Witness 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 Verify Witness use?

Verify Witness 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 Verify Witness use?

About 472 tokens (SKILL.md is roughly 1.9k 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 Verify Witness?

Skills that share tags, products or a category with Verify Witness: Azsdk Common Prepare Release Plan (Azure/azure-sdk-for-android, 121 stars), Azsdk Common Prepare Release Plan (Azure/azure-sdk-tools, 134 stars), Roam Release Readiness (Cranot/roam-code, 517 stars) and Run Nx Generator (nrwl/nx, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verify Witness?

ruvnet (a GitHub user) maintains it in ruvnet/metaharness, which has 696 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 10, 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.