agentmods.dev

macwhisper-mcp-server: Instructions file for Claude Code

CLAUDE.md

macwhisper-mcp-server CLAUDE.md is an instructions file for Claude Code from docdyhr/macwhisper-mcp-server. It costs 2,378 tokens per session, scanned A, original, MIT.

A project instruction document for a local MCP server that sends audio to MacWhisper for transcription, turning spoken recordings into text.

In plain words
What is it for?
Use it when working on the MacWhisper MCP server, its optional whisper-cpp transcription engine, tests, linting, or release setup.
Why use it?
It gives coding agents the repository context, current status, development commands, and test information they need before making changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is docdyhr/macwhisper-mcp-server's own configuration. It tells Claude Code how to work on macwhisper-mcp-server 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 macwhisper-mcp-server configures →

not rated 2repo today A scan 2,378 tokens original MIT
View source ↗ docdyhr/macwhisper-mcp-server
Reuse

Borrowing it

Nothing to install: this file belongs to docdyhr/macwhisper-mcp-server. 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/docdyhr/macwhisper-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/docdyhr/macwhisper-mcp-server

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 macwhisper-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/docdyhr/macwhisper-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/docdyhr/macwhisper-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/docdyhr/macwhisper-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/docdyhr/macwhisper-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,378 This file is loaded in full into every session.
When invoked 2,378 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02378 $0.02378
Opus 5 $0.01189 $0.01189
Sonnet 5 $0.00476 $0.00476
Haiku 4.5 $0.00238 $0.00238

Measured 8d ago against content hash d6f3f289d18c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

macwhisper-mcp-server CLAUDE.md scanned grade A with 1 finding 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 8d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

├── test_watcher.py # FolderWatcher tests, subprocess.run mocked
CLAUDE.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Context for Claude Code working on this repo. Read this first.

What this is

A local MCP server that exposes MacWhisper transcription to Claude Desktop. Audio → MacWhisper → MCP → Claude. Fully local, fully private. An optional whisper-cpp engine is also available (engine="whisper-cpp") that bypasses MacWhisper entirely — see PRD §3/§8. See PRD.md for the full spec and TODO.md for the roadmap.

Current status (2026-08-11)

v1.2.0 — 7 MCP tools, 96 tests green. Repo public. Published on PyPI, MCP Registry, and Homebrew tap (docdyhr/tap).

Verified working:

  • Python 3.13.13 venv at .venv/ with fastmcp==3.4.7
  • Package imports cleanly (macwhisper_mcp.{config,transcribe,server,watcher})
  • MacWhisper 14.6 (1472) installed via brew install --cask macwhisper (was 13.20/1410 — corrected 2026-08-11; mw's CLI has grown --language, --format json/srt/vtt/..., --timestamps, --speakers since the last PRD investigation, see PRD §11)
  • CLI at /usr/local/bin/mw (symlink → /Applications/MacWhisper.app/Contents/MacOS/mw); mw is on PATH. config.py auto-detects the app-bundle path and uses it directly.
  • MCP initialize + tools/list handshake works over stdio.
  • Live transcription round-trip confirmed via synthetic MCP client — 13.6s on a short Danish clip, UTF-8 clean. See docs/live-tests.md.
  • 96/96 tests pass (pytest -q)
  • CI green on every push (GitHub Actions, macos-latest, Python 3.13)
  • CodeQL SAST scan enabled and clean
  • Published: PyPI (pip install macwhisper-mcp-server) and MCP Registry (io.github.docdyhr/macwhisper-mcp-server)
  • awesome-mcp-servers PR #5397 open (waiting on maintainer)

Dev commands

source .venv/bin/activate

# Tests + lint
pytest -q
ruff check .
ruff format .

# Run the server standalone (stdio — it will sit idle waiting for MCP traffic)
python -m macwhisper_mcp.server

# Smoke-test the MCP handshake without Claude Desktop
# (pattern lives in git history / this file's discussion)

Read the full file on GitHub · 101 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. 8d ago First seen · 101 lines · 2,378 tokens per session scan A d6f3f289d18c

Subscribe to this mod's changes

macwhisper-mcp-server CLAUDE.md is an instructions file published in the GitHub repository docdyhr/macwhisper-mcp-server (2 stars, last pushed today), licensed MIT. It adds 2,378 tokens to every session, about $0.0119 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens