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.
/plugin marketplace add ruvnet/metaharnessnpx agentmods add plugins/ruvnet/metaharness/kimi-k3-harnessgit 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/plugins/ruvnet/metaharness/kimi-k3-harness)<a href="https://agentmods.dev/plugins/ruvnet/metaharness/kimi-k3-harness"><img src="https://agentmods.dev/badge/plugins/ruvnet/metaharness/kimi-k3-harness.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
kimi-k3-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 7d 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
{
"name": "kimi-k3-harness",
"version": "0.1.0",
"description": "Repo-aware coding agent harness for kimi-k3-in-c — Kimi K3 (2.78T-param) inference in portable C99: one CPU, 8 GB RAM, no BLAS, no framework, no GPU",
"author": {
"displayName": "Generated by metaharness",
"url": "https://www.npmjs.com/package/metaharness"
},
"license": "MIT",
"categories": [
"agent-harness",
"metaharness-scaffold",
"Engineering",
"software-engineering"
],
"tags": [
"metaharness",
"agent-harness",
"vertical:coding",
"software-engineering"
],
"homepage": "https://github.com/ruvnet/agent-harness-generator"
}
What it installs
The manifest is a name and a version. 2 skills, 2 commands travel with it, and installing the plugin installs all of them — 75 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 7d ago First seen · 24 lines scan A 9403e65b3a4d
kimi-k3-harness is a plugin published in the GitHub repository ruvnet/metaharness (631 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
claude-flow
Enterprise AI agent orchestration plugin with 150+ commands, 74+ specialized agents, SPARC methodology, swarm coordination, GitHub integration, and neural training capabilities.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
knowledge-work-plugins marketplace
Plugin marketplace listing 98 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
container
Teaches Claude container's command surface and how it maps to Docker, Lima, Colima, and Podman on macOS.