agentmd CLAUDE.md

A project guide for Claude Code, documenting the codebase, Python setup, build, test, lint, directory, naming, and commit conventions.

In plain words
What is it for?
Use it when working on the agentmd Python project, especially to install dependencies, run tests, check formatting, and follow repository conventions.
Why use it?
It gives the coding agent project-specific instructions instead of making it infer them each time.

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/mikiships/agentmd/claude-md
Clone the repo
git clone --depth 1 https://github.com/mikiships/agentmd
Per session 557 This file is loaded in full into every session.
When invoked 557 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 $0.00557 $0.00557
Opus 5 $0.00279 $0.00279
Sonnet 5 $0.00111 $0.00111
Haiku 4.5 $0.00056 $0.00056

Measured 3d ago against content hash ea3cd5bbed2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentmd 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Agent context for Claude Code. Keep this file up to date as the project evolves.

Project Overview

Primary languages: Python Package managers: pip CI: GitHub Actions

Build, Test, and Lint Commands

Install dependencies:

pip install -e '.[dev]'

Run tests:

python3 -m pytest tests/ -x

Lint / format:

ruff check . && ruff format --check .

Directory Structure

Top-level directories: .github, agentmd, tests Test roots: tests Most-changed directories: agentmd, tests, README.md, pyproject.toml, progress-log.md

Conventions Inferred from Codebase

Commit prefix style: feat, fix, chore, docs, feat(d3) (follow this pattern) Common file extensions: .pyc, .py, .md, .toml, .yml

  • Python: use type hints on all public functions
  • Python: snake_case for functions/variables, PascalCase for classes
  • Tests: files named test_*.py, functions named test_*

Claude Code Tips

  • Use /compact when context grows large mid-session to avoid token limit errors.
  • Use /review before committing to get a focused code review.
  • Use /init in a new checkout to re-read this file and orient yourself.
  • Open multiple files in a single message when changes span files — reduces round-trips.
  • Prefer small, targeted edits over full-file rewrites when touching existing code.
  • After every non-trivial change, run python3 -m pytest tests/ -x to confirm nothing broke.

Style Guide

  • All public functions and methods must have type annotations.
  • Docstrings: use triple-quoted strings on public classes and functions.
  • Maximum line length: 100 characters (unless project config says otherwise).
  • Imports: standard library first, third-party second, local last (separated by blank lines).
  • Linting enforced by ruff — run ruff check . before committing.

Anti-Patterns to Avoid

  • Do not make broad refactors outside the scope of the current task.
  • Do not delete or skip existing tests to make CI green.
  • Do not add dependencies without noting them in the commit message.
  • Do not use bare except: — always catch specific exceptions.
  • Do not use mutable default arguments (e.g., def f(x=[])).

Read the full file on GitHub · 57 lines

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 · 57 lines · 557 tokens per session scan A ea3cd5bbed2d

Subscribe to this mod's changes

agentmd CLAUDE.md is an instructions file published in the GitHub repository mikiships/agentmd (12 stars, last pushed 5mo ago), licensed MIT. It adds 557 tokens to every session, about $0.0028 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.