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 agentmods add instructions/iowarp/clio-kit/claude-mdgit 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/instructions/iowarp/clio-kit/claude-md)<a href="https://agentmods.dev/instructions/iowarp/clio-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/iowarp/clio-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.04847 | $0.04847 |
| Opus 5 | $0.02423 | $0.02423 |
| Sonnet 5 | $0.00969 | $0.00969 |
| Haiku 4.5 | $0.00485 | $0.00485 |
Grade A, and why
clio-kit CLAUDE.md 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 4d 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 — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
CLIO Kit is part of the IoWarp platform's tooling layer for AI agents. It is a production-grade monorepo containing 15+ MCP (Model Context Protocol) servers designed for scientific computing research, with plans to expand to additional agent capabilities (skills, plugins, extensions). The project enables AI agents and LLMs to interact with HPC resources, scientific data formats, and research datasets through a standardized protocol.
The repository uses a unified launcher with auto-discovery pattern: each MCP server is independently developed and tested, but all are launched through a single clio-kit <server-name> command.
Platform Context: CLIO Kit is the tooling layer of the IoWarp platform, providing comprehensive agent capabilities beyond just MCP servers.
Key Technologies: FastMCP 3.0, Python 3.10+, UV package manager, Pydantic, pytest, Ruff
Project Structure
clio-kit/ # Monorepo root
├── src/clio_kit/ # Unified launcher CLI
├── clio-kit-mcp-servers/ # 16 independent MCP servers
│ ├── hdf5/ ⭐ # Flagship server (v2.0, 28 tools)
│ ├── pandas/ # Data analysis operations
│ ├── slurm/ # HPC job management
│ ├── arxiv/ # Research paper fetching
│ ├── chronolog/ # Distributed logging
│ ├── compression/ # File compression
│ ├── darshan/ # I/O performance analysis
│ ├── jarvis/ # Data pipeline management
│ ├── lmod/ # Environment modules
│ ├── ndp/ # Dataset discovery
│ ├── node-hardware/ # System hardware info
│ ├── parallel-sort/ # Large file sorting
│ ├── paraview/ # Scientific visualization
│ ├── parquet/ # Parquet file handling
│ ├── plot/ # Data visualization
│ ├── adios/ # ADIOS2 data I/O
│ └── [each has its own pyproject.toml, dependencies, tests]
├── clio-agentic-search/ # Standalone hybrid retrieval engine (not an MCP server)
├── clio-kit-website/ # Docusaurus documentation site
├── scripts/ # Utility scripts (generate_docs.py, etc)
├── .github/workflows/ # CI/CD automation
└── [root config files] # pyproject.toml, uv.lock
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.
- 4d ago First seen · 534 lines · 4,847 tokens per session scan A 6e7b45fc4c33
clio-kit CLAUDE.md is an instructions file published in the GitHub repository iowarp/clio-kit (26 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 4,847 tokens to every session, about $0.0242 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.
Other instructions, from other repositories
obsidian-vault-mcp CLAUDE.md
Claude Code instructions for ebullient/obsidian-vault-mcp, covering obsidian vault mcp, code style and qa.
context-engineering CLAUDE.md
Instructions for timothywarner-org/context-engineering, covering claude.md, working style (tim's preferences), project overview, development commands and warnerco schematica.
slivingdoc AGENTS.md
AGENTS.md instructions for baalimago/slivingdoc, covering agents.md — slivingdoc, architecture, package map, event flow and startup wiring (main.go).
mcp-redmine-rest CLAUDE.md
Claude Code instructions for alsimoes/mcp-redmine-rest, covering claude.md, what this is, layout (src-layout), tool registration pattern and deliberately missing tools.
qa-use CLAUDE.md
Instructions for desplega-ai/qa-use, covering claude.md, project map and tech stack.
vision-memory-mcp CLAUDE.md
Claude Code instructions for putervision/vision-memory-mcp, covering visual memory (vision-memory-mcp), 1. mandatory workflow & priority, 2. tool reference summary (15 core mcp tools), state memory (state-memory-mcp) and 1. priority order.