Borrowing it
Nothing to install: this file belongs to jason-weddington/karabiner-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.
curl -O https://raw.githubusercontent.com/jason-weddington/karabiner-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/jason-weddington/karabiner-mcpWrote 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.
[](https://agentmods.dev/instructions/jason-weddington/karabiner-mcp/claude-md)<a href="https://agentmods.dev/instructions/jason-weddington/karabiner-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jason-weddington/karabiner-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.
<a href="https://agentmods.dev/instructions/jason-weddington/karabiner-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jason-weddington/karabiner-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00635 | $0.00635 |
| Opus 5 | $0.00318 | $0.00318 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
karabiner-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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build and Test Commands
uv sync # Install dependencies
uv run pytest # Run tests
uv run pytest --cov=karabiner_mcp # Tests with coverage
uv run ruff check . # Lint
uv run ruff format . # Format
uv run mypy src/ # Type check
Project Structure
karabiner_mcp/
├── src/karabiner_mcp/
│ ├── __main__.py # Entry point: create_server().run(transport="stdio")
│ ├── server.py # FastMCP creation, lifespan, instructions
│ ├── config.py # Env vars: CONFIG_PATH, ASSETS_DIR, LOG_LEVEL
│ ├── tools/
│ │ ├── rules.py # list_rules, add_rule, edit_rule, remove_rule, toggle_rule
│ │ ├── profiles.py # list_profiles, select_profile
│ │ └── keycodes.py # search_key_codes
│ └── service/ # Pure service layer (copied from karabiner_pro_ui)
│ ├── karabiner.py # Config I/O, rule CRUD, asset management
│ ├── compiler.py # IR <-> Karabiner JSON compiler/decompiler
│ ├── ir.py # ManipulatorIR Pydantic models with validation
│ └── keycodes.py # Key code data (~180 codes, modifiers, pointing buttons)
└── tests/
├── conftest.py # Fixtures: karabiner_env (temp dir), mock_ctx
├── test_rules.py # Rule tool tests
├── test_profiles.py # Profile tool tests
└── test_keycodes_tool.py # Key code search tests
Architecture
- FastMCP server with stdio transport, registered in
~/.claude.json - Lifespan resolves config/asset paths; tools read karabiner.json fresh each call
- Service layer (
service/) is pure functions with zero framework dependencies - IR layer handles all Karabiner JSON serialization gotchas (see
karabiner_research.mdin karabiner_pro_ui) - Error handling: tools return error strings, not exceptions
MCP Registration
"karabiner-mcp": {
"type": "stdio",
"command": "uv",
"args": ["run", "--directory", "/Users/jason/git/karabiner_mcp", "karabiner-mcp"]
}
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.
- 10d ago First seen · 54 lines · 635 tokens per session scan A 70c404b6e625
karabiner-mcp CLAUDE.md is an instructions file published in the GitHub repository jason-weddington/karabiner-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 635 tokens to every session, about $0.0032 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).