What is mcp-whisper-transcription CLAUDE.md?

A set of project instructions for an AI coding assistant working on a Whisper transcription server. Whisper is software that converts recorded speech into text; the instructions also describe the project’s architecture and memory systems.

It helps work with the FastMCP server, audio transcription code, formatting utilities, tests, and local or shared memory searches.

It tells the assistant how this repository is organised and where to look for project-specific or reusable knowledge.

How galacoder/mcp-whisper-transcription configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to galacoder/mcp-whisper-transcription. 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/galacoder/mcp-whisper-transcription/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/galacoder/mcp-whisper-transcription

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/galacoder/mcp-whisper-transcription/claude-md/github.svg)](https://agentmods.dev/instructions/galacoder/mcp-whisper-transcription/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/galacoder/mcp-whisper-transcription/claude-md"><img src="https://agentmods.dev/badge/instructions/galacoder/mcp-whisper-transcription/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/galacoder/mcp-whisper-transcription/claude-md"><img src="https://agentmods.dev/badge/instructions/galacoder/mcp-whisper-transcription/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,054 This file is loaded in full into every session.

When invoked 2,054 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.02054	$0.02054
Opus 5	$0.01027	$0.01027
Sonnet 5	$0.00411	$0.00411
Haiku 4.5	$0.00205	$0.00205

Measured 9d ago against content hash eaf9fd8dd56b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-whisper-transcription 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 9d 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 · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Concise Project Guide for Claude Code

This file provides essential guidance for Claude Code (Sonnet & Opus 4) when working with this repository.

🏗️ Project Architecture

MCP Server for Whisper Transcription:

Main Server: FastMCP-based server (src/whisper_mcp_server.py)
Core Transcriber: MLX Whisper implementation (transcribe_mlx.py)
Utilities: Audio processing, formatting (whisper_utils.py)
Tests: Comprehensive test suite (test_*.py)

🧠 Memory Strategy

Dual-Memory System

Local (OpenMemory): Project-specific knowledge, quick access
Global (Graphiti): Cross-project patterns, reusable solutions

Quick Reference

Local: search_memory("[query]") - This project's specifics
Global: mcp__graphiti-memory__search_memory_nodes --query="[pattern]" --group_ids=["global_patterns"]

What Goes Where

Local Memory (This Project):

MCP server patterns, FastMCP usage
Whisper transcription workflows
Audio processing techniques
Project-specific configurations

Global Memory (Your Knowledge Base):

MCP protocol patterns
FastMCP architectural patterns
Audio/video processing patterns
Python async patterns

🚀 Mandatory Task Workflows

Task Start Checklist

ALWAYS execute in order:

Check memories:
- Local: search_memory("task_context [task_id]")
- Global: mcp__graphiti-memory__search_memory_nodes --query="[technology] patterns" --group_ids=["global_patterns"]
mcp__task-master__get_task --id="[task_id]" --projectRoot="/Users/sangle/Dev/action/projects/mcp-servers/tools/mcp-whisper-transcription"
Check/create tag context with mcp__task-master__list_tags
If unfamiliar tech:
- Use Context7: mcp__context7__resolve-library-id --libraryName="[technology]" then mcp__context7__get-library-docs --context7CompatibleLibraryID="[resolved_id]"
- Web search: WebSearch --query="[topic] best practices implementation"
- Save findings: mcp__openmemory__add_memories --text="Research: [findings]"
If no subtasks: mcp__task-master__analyze_project_complexity --ids="[task_id]"
mcp__task-master__set_task_status --id="[task_id]" --status="in-progress"
Create TodoWrite for task breakdown
Search implementation patterns in both memories

Read the full file on GitHub · 236 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.

9d ago First seen · 236 lines · 2,054 tokens per session scan A eaf9fd8dd56b

Subscribe to this mod's changes

mcp-whisper-transcription CLAUDE.md is an instructions file published in the GitHub repository galacoder/mcp-whisper-transcription (1 stars, last pushed 1y ago), licensed MIT. It adds 2,054 tokens to every session, about $0.0103 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.

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

mcp-whisper-transcription: Instructions file for Claude Code