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/universal-tool-calling-protocol/python-utcp/claude-mdgit clone --depth 1 https://github.com/universal-tool-calling-protocol/python-utcpWhat 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 | $0.00871 | $0.00871 |
| Opus 5 | $0.00436 | $0.00436 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
python-utcp 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 yesterday.
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 — 113 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
This is the Python implementation of the Universal Tool Calling Protocol (UTCP), a flexible and scalable standard for defining and interacting with tools across various communication protocols. UTCP emphasizes scalability, interoperability, and ease of use compared to other protocols like MCP.
Development Commands
Building and Installation
# Create virtual environment and install dependencies
conda create --name utcp python=3.10
conda activate utcp
pip install -r requirements.txt
python -m pip install --upgrade pip
# Build the package
python -m build
# Install locally
pip install dist/utcp-<version>.tar.gz
Testing
# Run all tests
pytest
# Run tests with coverage
pytest --cov=src/utcp
# Run specific plugin tests
pytest plugins/communication_protocols/http/tests/
pytest plugins/communication_protocols/websocket/tests/
Development Dependencies
- Install dev dependencies:
pip install -e .[dev] - Key dev tools: pytest, pytest-asyncio, pytest-aiohttp, pytest-cov, coverage, fastapi, uvicorn
Architecture Overview
Core Components
Client Architecture (src/utcp/client/):
UtcpClient: Main entry point for UTCP ecosystem interactionUtcpClientConfig: Pydantic model for client configurationClientTransportInterface: Abstract base for transport implementationsToolRepository: Interface for storing/retrieving tools (default:InMemToolRepository)ToolSearchStrategy: Interface for tool search algorithms (default:TagSearchStrategy)
Shared Models (src/utcp/shared/):
Tool: Core tool definition with inputs/outputs schemasProvider: Defines communication protocols for toolsUtcpManual: Contains discovery information for tool collectionsAuth: Authentication models (API key, Basic, OAuth2)
Transport Layer (src/utcp/client/transport_interfaces/):
Each transport handles protocol-specific communication:
HttpClientTransport: RESTful HTTP/HTTPS APIsCliTransport: Command Line Interface toolsSSEClientTransport: Server-Sent EventsStreamableHttpClientTransport: HTTP chunked transferMCPTransport: Model Context Protocol interoperabilityTextTransport: Local file-based tool definitionsGraphQLClientTransport: GraphQL APIs
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.
- yesterday First seen · 113 lines · 871 tokens per session scan A a52f328d559d
python-utcp CLAUDE.md is an instructions file published in the GitHub repository universal-tool-calling-protocol/python-utcp (646 stars, last pushed 2mo ago), licensed MPL-2.0. It adds 871 tokens to every session, about $0.0044 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
stealth-browser-mcp AGENTS.md
Instructions for vibheksoni/stealth-browser-mcp, covering agent instructions, start here, recommended proxy services, environment and validation.
Graph-It-Live CLAUDE.md
Instructions for magic5644/Graph-It-Live, covering claude.md, commands, build, test and e2e (real vs code electron instance).
swapper-toolkit CLAUDE.md
Instructions for swapperfinance/swapper-toolkit, covering swapper ai agent toolkit, what is swapper finance?, repository structure, how the deposit skill works and deeplink format.
hermes-local-knowledge AGENTS.md
Instructions for stepanov1975/hermes-local-knowledge, covering agent instructions for hermes-local-knowledge, before editing, documented public boundaries, current owners and product, ranking, and privacy invariants.
garmin-mcp AGENTS.md
AGENTS.md instructions for davidmosiah/garmin-mcp, covering agent development notes, scope, commands and rules.
tokenlean CLAUDE.md
Instructions for edimuj/tokenlean, covering tokenlean, project structure, adding a new tool, conventions and shell completions.