validate-harness

validate-harness is a skill for Claude Code from ruvnet/metaharness. It costs 50 tokens per session (410 once invoked), scanned A, original, MIT.

A single release-readiness check for a software harness, meaning a project that runs or coordinates development tools. It combines checks for files, signatures, unsafe hardcoded paths, MCP server settings, and Google Cloud secrets.

In plain words
What is it for?
Use it before releasing a harness to check its manifest and host files, verify an Ed25519 witness signature, find hardcoded machine-specific paths, validate MCP entries, and confirm required Google Cloud credentials and secrets.
Why use it?
It replaces several separate checks with one command and reports which release requirement passed, failed, or needs attention.

Skill for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions Codex.

Part of the agent-harness-generator plugin — 14 skills, 1 plugin shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/ruvnet/metaharness/validate-harness
Any agent
npx skills add ruvnet/metaharness --skill validate-harness
Clone the repo
git clone --depth 1 https://github.com/ruvnet/metaharness

Made for: Claude Code.

Or install agent-harness-generator, the plugin that ships this one along with the rest of its 14 skills, 1 plugin.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for validate-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruvnet/metaharness/validate-harness.svg)](https://agentmods.dev/skills/ruvnet/metaharness/validate-harness)
Your own site
<a href="https://agentmods.dev/skills/ruvnet/metaharness/validate-harness"><img src="https://agentmods.dev/badge/skills/ruvnet/metaharness/validate-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 410 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.00410
Opus 5 $0.00025 $0.00205
Sonnet 5 $0.00010 $0.00082
Haiku 4.5 $0.00005 $0.00041

Measured 6d ago against content hash a2850a64ffc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

validate-harness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/skills/validate-harness/SKILL.md · 40 lines

What it actually says

validate-harness

Codex skill that runs the 5 release-readiness gates from harness validate.

What it checks

# Check What it does
1 doctor File shape + manifest sha256 + at-least-one host artifact
2 verify Witness manifest signature (Ed25519) — skipped if no witness yet
3 path-guard Scans your TS/JS/Rust files for hardcoded /tmp/, C:\, /Users/, /home/ — the original Windows /tmp bug regression class
4 mcp .mcp/servers.json entries have name + command
5 secrets gcloud auth list + project + NPM_TOKEN exist in GCP Secret Manager

Each check reports PASS / FAIL / WARN with a one-line detail. Exits 1 if any FAIL.

Usage from Codex

/validate-harness
/validate-harness path=./my-harness
/validate-harness path=./my-harness skip_gcp=true
/validate-harness secret=NPM_TOKEN_DEV

Equivalent CLI

harness validate ./my-harness --skip-gcp --secret=NPM_TOKEN_DEV

Why this exists

Before iter 20, you needed to remember to run harness doctor, harness verify, harness secrets check, and node scripts/path-guard.mjs separately. This is the single release-readiness gate.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 40 lines · 50 tokens per session scan A a2850a64ffc7

Subscribe to this mod's changes

validate-harness is a skill published in the GitHub repository ruvnet/metaharness (630 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 410 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.