agentmods.dev

uv-mcp: Instructions file for Claude Code

CLAUDE.md

uv-mcp CLAUDE.md is an instructions file for Claude Code from saadmanrafat/uv-mcp. It costs 515 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for working on uv-mcp, a server that exposes the `uv` Python project tool as typed tools for a coding agent.

In plain words
What is it for?
Use it when changing uv-mcp, adding or checking tools for Python projects, dependencies, environments, packaging, builds, or diagnostics. It also describes how to run tests, formatting checks, and tool-reference generation.
Why use it?
It gives contributors the project's commands, file layout, testing rules, and checks for keeping the tool coverage and generated documentation up to date.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is saadmanrafat/uv-mcp's own configuration. It tells Claude Code how to work on uv-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything uv-mcp configures →

not rated 19repo 3d ago A scan 515 tokens original Apache-2.0
View source ↗ saadmanrafat/uv-mcp saadman.dev
Reuse

Borrowing it

Nothing to install: this file belongs to saadmanrafat/uv-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/saadmanrafat/uv-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/saadmanrafat/uv-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for uv-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/saadmanrafat/uv-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/saadmanrafat/uv-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/saadmanrafat/uv-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/saadmanrafat/uv-mcp/claude-md/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.

agentmods 80×15 button for uv-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/saadmanrafat/uv-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/saadmanrafat/uv-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 515 This file is loaded in full into every session.
When invoked 515 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00515 $0.00515
Opus 5.5 $0.00206 $0.00206
Sonnet 5.5 $0.00103 $0.00103
Haiku 4.5 $0.00052 $0.00052

Measured 3d ago against content hash 491319841fbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

uv-mcp 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 3d 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.

CLAUDE.md · 34 lines

What it actually says

Working on uv-mcp

uv-mcp is an MCP server (PyPI: uv-mcp-server, import: uv_mcp) that exposes the uv CLI as typed tools.

Commands

uv sync                          # install dev environment
uv run pytest -m "not network"   # fast suite (needs uv on PATH, no internet)
uv run pytest                    # full suite (downloads from PyPI)
uv run ruff check src tests && uv run ruff format --check src tests
uv run uv-mcp-server --list-tools
uv run python scripts/gen_tool_reference.py   # regenerate docs/src/content/docs/reference/tools.md

Layout

  • src/uv_mcp/server.py: FastMCP app factory (create_server), agent INSTRUCTIONS, CLI main.
  • src/uv_mcp/registry.py: @uv_tool(...) decorator. Declares MCP annotations and the toolset.
  • src/uv_mcp/tools/*.py: one module per uv area (project, workspace, python, pip, env, uvtools, build, cache, auth, meta, diagnostics).
  • src/uv_mcp/coverage.py: every uv command mapped to its tool (or uv_info, uv_command, or blocked). tests/test_coverage.py fails when the installed uv has a command missing from it.
  • src/uv_mcp/runner.py: the only place a subprocess is started. No shell, scrubbed env, timeouts, redaction.
  • src/uv_mcp/security.py: argument validation, path confinement, secret redaction.
  • src/uv_mcp/diagnostics.py: uv_project_info / uv_diagnose / uv_repair logic.

Rules for new tools

  1. Name it after the uv command (uv pip tree becomes uv_pip_tree) and set honest annotations in @uv_tool.
  2. Build argv with Args; validate every user value (opt, many, positional already do). Never use a shell.
  3. Resolve paths with security.resolve_path / project_dir so confinement applies.
  4. Secrets go through env= or stdin_data= plus secrets=[...], never argv.
  5. Keep parameter descriptions short; rarely used flags belong in extra_args.
  6. Map it in coverage.py, add a test, then regenerate the tool reference.
Changes

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.

  1. 3d ago First seen · 34 lines · 515 tokens per session scan A 491319841fbb

Subscribe to this mod's changes

uv-mcp CLAUDE.md is an instructions file published in the GitHub repository saadmanrafat/uv-mcp (19 stars, last pushed 3d ago), licensed Apache-2.0. It adds 515 tokens to every session, about $0.0021 per session on Opus 5.5. 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 2026-11-03.

LanguagesPythongemini-cli-extensionsmcpuv
Related

uv-mcp CLAUDE.md compared with instructions from other repositories

uv-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
uv-mcp CLAUDE.mdsaadmanrafat/uv-mcpInstructions file193d agoApache-2.0A515Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode