python-docs-mcp-server CLAUDE.md

A repository instruction file points contributors to the canonical guidance for a server that lets agents access Python documentation.

In plain words
What is it for?
It is for guiding work on the Python documentation server and its MCP, OpenAI, Python SDK, testing, and release integrations.
Why use it?
It keeps instructions in one authoritative file and identifies the documentation, testing, and release procedures to follow.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/ayhammouda/python-docs-mcp-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/ayhammouda/python-docs-mcp-server
Per session 151 This file is loaded in full into every session.
When invoked 151 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00151 $0.00151
Opus 5 $0.00076 $0.00076
Sonnet 5 $0.00030 $0.00030
Haiku 4.5 $0.00015 $0.00015

Measured 2d ago against content hash 8d12f8f7ebd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-docs-mcp-server 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.

CLAUDE.md · 17 lines

What it actually says

Claude Compatibility Notes

Use AGENTS.md as the canonical repository guidance.

This file is intentionally thin so Claude-compatible tools can find the repo rules without carrying a second copy of project policy.

Key points:

  • Start with README.md and CONTRIBUTING.md for current repo truth.
  • Treat .planning/ as archival context, not live instructions.
  • Use official docs first for MCP, OpenAI/Codex, and Python SDK behavior.
  • Do not add extra MCP servers or repo-local custom skills unless there is a clear, repeated project need.
  • Use .github/INTEGRATION-TEST.md for manual MCP QA and .github/RELEASE.md for release-specific steps.
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. 2d ago First seen · 17 lines · 151 tokens per session scan A 8d12f8f7ebd9

Subscribe to this mod's changes

python-docs-mcp-server CLAUDE.md is an instructions file published in the GitHub repository ayhammouda/python-docs-mcp-server (7 stars, last pushed 8d ago), licensed MIT. It adds 151 tokens to every session, about $0.0008 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.