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.
npx agentmods add instructions/fiveohhwon/summarize-mcp/claude-mdgit clone --depth 1 https://github.com/FiveOhhWon/summarize-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/fiveohhwon/summarize-mcp/claude-md)<a href="https://agentmods.dev/instructions/fiveohhwon/summarize-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/fiveohhwon/summarize-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.00464 | $0.00464 |
| Opus 5 | $0.00232 | $0.00232 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
summarize-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 4d 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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Common Development Commands
Running the Server
python -m summarize_mcp- Run the MCP serverpython test.py- Run the test scriptpip install -r requirements.txt- Install dependenciespip install -e .- Install in development mode
Before Publishing
- Test the server with
python test.py - Ensure all dependencies are listed in
requirements.txtandpyproject.toml
Architecture Overview
This is a Model Context Protocol (MCP) server that provides text-to-speech functionality using OpenAI's TTS API. The architecture consists of:
-
MCP Server Implementation (
src/summarize_mcp/server.py):- Uses stdio transport for communication with MCP clients
- Implements three tools:
play_summary,set_voice, andset_tone - Manages persistent user preferences in
~/.summarize-mcp-state.json
-
Cross-Platform Audio Playback:
- macOS: Uses built-in
afplay - Windows: Uses PowerShell with Windows Media Player
- Linux: Auto-detects available players (mpg123, sox, ffmpeg, vlc, alsa)
- Fallback: Opens with system default audio application
- macOS: Uses built-in
-
File Management:
- Creates temporary MP3 files in system temp directory
- Automatic cleanup after 10 seconds
- Purges files older than 1 hour on startup
-
State Management:
- Persists user voice and tone preferences between sessions
- Uses Pydantic for runtime validation of all inputs
- Preferences override defaults unless explicitly specified in tool calls
Key Implementation Details
- Written in Python 3.8+ with async/await support
- Uses Pydantic for data validation (Python equivalent of Zod)
- Environment variable
OPENAI_API_KEYis required - Debug logging available via
DEBUG=trueenvironment variable - Can be run directly with
python -m summarize_mcpor installed as a package
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.
- 4d ago First seen · 48 lines · 464 tokens per session scan A da427f045237
summarize-mcp CLAUDE.md is an instructions file published in the GitHub repository FiveOhhWon/summarize-mcp (1 stars, last pushed 1y ago), licensed MIT. It adds 464 tokens to every session, about $0.0023 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
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.