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/gianlucamazza/mcp_python_toolbox/claude-mdgit clone --depth 1 https://github.com/gianlucamazza/mcp_python_toolboxWhat 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 | $0.00253 | $0.00253 |
| Opus 5 | $0.00127 | $0.00127 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
mcp_python_toolbox 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 2d 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
MCP Python Toolbox - Development Guidelines
Build/Test/Lint Commands
- Install dev dependencies:
pip install -e ".[dev]" - Run all tests:
pytest - Run single test:
pytest tests/path/to/test_file.py::test_function_name -v - Type checking:
mypy src/mcp_python_toolbox - Linting:
pylint src/mcp_python_toolbox - Format code:
black src/mcp_python_toolbox
Code Style Guidelines
- Line length: 100 characters (Black configuration)
- Python version: 3.7+
- Formatting: Use Black for automatic formatting
- Imports: Standard library first, then third-party, then local modules
- Types: All functions must have type annotations (disallow_untyped_defs=true)
- Naming:
- Classes: PascalCase
- Functions/variables: snake_case
- Constants: UPPER_CASE
- Error handling: Use specific exceptions with descriptive error messages
- Documentation: Docstrings for all modules, classes, and functions using """triple quotes"""
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.
- 2d ago First seen · 22 lines · 253 tokens per session scan A bd157d487152
mcp_python_toolbox CLAUDE.md is an instructions file published in the GitHub repository gianlucamazza/mcp_python_toolbox (9 stars, last pushed 1mo ago), licensed MIT. It adds 253 tokens to every session, about $0.0013 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 2026-08-31.
Other instructions, from other repositories
grounded-code-mcp AGENTS.md
AGENTS.md instructions for michaelalber/grounded-code-mcp, covering grounded-code-mcp — project context, project overview, technology stack, architecture and key files.
grounded-code-mcp CLAUDE.md
Claude Code instructions for michaelalber/grounded-code-mcp, covering claude.md, project overview, technology stack, architecture and key files.
trilium-fastmcp AGENTS.md
AGENTS.md instructions for eliassoares/trilium-fastmcp, covering agents.md, project overview, project structure, commands and code style.
trilium-fastmcp CLAUDE.md
Claude Code instructions for eliassoares/trilium-fastmcp, covering claude.md, project overview, project structure, commands and code style.
yt-transcript-mcp CLAUDE.md
Claude Code instructions for alex2zimmermann-ux/yt-transcript-mcp, covering youtube transcript mcp server, projekt, architektur, wichtige dateien and befehle.
mcp_server_code_extractor CLAUDE.md
Claude Code instructions for ctoth/mcp_server_code_extractor, covering claude.md, development commands, run all tests using pytest, run individual test files and quick functional test of core mcp server.