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.
git clone --depth 1 https://github.com/iowarp/clio-kitWrote 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/iowarp/clio-kit/marketplace)<a href="https://agentmods.dev/plugins/iowarp/clio-kit/marketplace"><img src="https://agentmods.dev/badge/plugins/iowarp/clio-kit/marketplace/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/plugins/iowarp/clio-kit/marketplace"><img src="https://agentmods.dev/badge/plugins/iowarp/clio-kit/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
clio-kit marketplace 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.
How it starts
The opening of the file, as written. The whole thing — 1,180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "clio-kit",
"owner": {
"name": "IoWarp Team - Gnosis Research Center",
"email": "[email protected]"
},
"metadata": {
"description": "CLIO Kit - A meta-marketplace for scientific MCP servers, skills, plugins, agents, and community contributions",
"version": "2.11.0"
},
"plugins": [
{
"name": "clio-adios",
"source": "./plugins/clio-adios",
"description": "Fetch and analyze BP5 data files using ADIOS2. Access scientific data, metadata, and attributes for research and analysis purposes.",
"version": "2.2.5",
"category": "scientific",
"keywords": [
"scientific-computing",
"adios2",
"bp5",
"data-io",
"hpc"
],
"license": "BSD-3-Clause",
"repository": "https://github.com/iowarp/clio-kit"
},
{
"name": "clio-arxiv",
"source": "./plugins/clio-arxiv",
"description": "Search arXiv by topic, author, title or date, read paper details, and export BibTeX or PDFs.",
"version": "2.2.5",
"category": "scientific",
"keywords": [
"research",
"arxiv",
"papers",
"literature-search"
],
"license": "BSD-3-Clause",
"repository": "https://github.com/iowarp/clio-kit"
},
{
"name": "clio-chronolog",
"source": "./plugins/clio-chronolog",
"description": "Record and retrieve agent interactions in a ChronoLog log store.",
"version": "2.0.3",
"category": "scientific",
"keywords": [
"logging",
"distributed-systems",
"hpc",
"time-series"
],
"license": "BSD-3-Clause",
"repository": "https://github.com/iowarp/clio-kit"
},
{
"name": "clio-compression",
"source": "./plugins/clio-compression",
"description": "Compress and decompress files with gzip and report the compression ratio.",
"version": "2.2.5",
"category": "general",
"keywords": [
The plugins it lists here
This marketplace lists 9 plugins kept in the same repository. Each has its own page, its own measurements and its own install command.
- Plugin clio-analysis-skills 4 inside A not measured
- Plugin clio-dataset-report 2 inside A not measured
- Plugin clio-geoscience-skills 3 inside A not measured
- Plugin clio-hpc-skills 3 inside A not measured
- Plugin clio-performance-skills 4 inside A not measured
- Plugin clio-research-skills 3 inside A not measured
- Plugin clio-coder-skills 39 inside A not measured
- Plugin clio-agents 2 inside A not measured
- Plugin clio-scientific-io-skills 3 inside A not measured
What ships with it
2 files beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +842 lines 452e6188df16
- 1mo ago First seen · 338 lines scan A ad20bc498ef8
clio-kit marketplace is a plugin published in the GitHub repository iowarp/clio-kit (30 stars, last pushed 8d ago), licensed BSD-3-Clause. 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
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
code-modernization
Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page…