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.
npx skills add ruvnet/metaharness --skill harness-secretsgit clone --depth 1 https://github.com/ruvnet/metaharnessWrote 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.
[](https://agentmods.dev/skills/ruvnet/metaharness/harness-secrets)<a href="https://agentmods.dev/skills/ruvnet/metaharness/harness-secrets"><img src="https://agentmods.dev/badge/skills/ruvnet/metaharness/harness-secrets/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ruvnet/metaharness/harness-secrets"><img src="https://agentmods.dev/badge/skills/ruvnet/metaharness/harness-secrets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00341 |
| Opus 5 | $0.00000 | $0.00170 |
| Sonnet 5 | $0.00000 | $0.00068 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
harness-secrets 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 9d 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.
What it actually says
harness-secrets
Codex skill for GCP Secret Manager — check / fetch / validate-token.
Modes
check
Validates the full GCP setup (gcloud on PATH, active project, auth principal, secret exists, WIF pool present). Use this when bootstrapping a new GCP project for publish.
/harness-secrets mode=check
/harness-secrets mode=check secret=NPM_TOKEN_DEV
/harness-secrets mode=check project=my-gcp-project secret=NPM_TOKEN
fetch
Fetches a secret value to stdout. Use in pipelines:
/harness-secrets mode=fetch secret=NPM_TOKEN
/harness-secrets mode=fetch secret=GH_TOKEN version=3
validate-token
Fetches NPM_TOKEN and runs npm whoami against the registry. No publish — just confirms the token isn't revoked. Use this BEFORE you tag a release.
/harness-secrets mode=validate-token
/harness-secrets mode=validate-token secret=NPM_TOKEN_STAGING
Equivalent CLI
harness secrets check --secret=NPM_TOKEN
harness secrets fetch NPM_TOKEN --version=3
harness secrets validate-token
Why this exists
So you can refresh + verify the publish-time GCP secret WITHOUT triggering a real publish.
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.
- 9d ago First seen · 48 lines · 0 tokens per session scan A 8ea9cc60cfd9
harness-secrets is a skill published in the GitHub repository ruvnet/metaharness (639 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 341 tokens. 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.
Other skills, from other repositories
vercel-deploy
Deploy an approved and tested committed web project to a Vercel preview and verify provider identity, commit, status and actual URL. Use for publishing a website preview; production needs separate approval, and feature building or browser QA belong to other skills.
C31-plan
Turn requirements into validated, executable plans. C31-brainstorm defines WHAT; C31-plan defines HOW — with coverage gates, wave analysis, and threat modeling.
C31-adopt-project
A guided workflow for researching a GitHub project and preparing a possible integration. It creates a report automatically, but waits for your confirmation before making changes.
C31-brainstorm
Brainstorming answers WHAT to build. It precedes planning, which answers HOW to build it.
C31-storm
A multi-perspective analysis method based on Stanford's STORM approach. It discovers relevant viewpoints, simulates discussion between them, maps disagreements, and produces a provisional judgment with confidence levels.
kimiim-cli
Use this skill for any interaction with Kimi Group Chat or its Sessions, including reading Group Rules, checking members and recent messages, replying in group/thread context, and handling Kimi IM files. MUST use this skill whenever the incoming message originates from Kimi Group Chat or its Sessions, or whenever the…