Borrowing it
Nothing to install: this file belongs to mahimailabs/voicegateway. 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/mahimailabs/voicegateway/main/CLAUDE.mdgit clone --depth 1 https://github.com/mahimailabs/voicegatewayWrote 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/mahimailabs/voicegateway/claude-md)<a href="https://agentmods.dev/instructions/mahimailabs/voicegateway/claude-md"><img src="https://agentmods.dev/badge/instructions/mahimailabs/voicegateway/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 5.1 | $0.01234 | $0.01234 |
| Opus 5 | $0.00617 | $0.00617 |
| Sonnet 5 | $0.00247 | $0.00247 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
voicegateway 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 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.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project
VoiceGateway: cost tracking and reconciliation for voice agents on LiveKit, Pipecat and OpenRTC. Meters the native STT, LLM, and TTS instances you pass to attach() / guard() across cloud providers (OpenAI, Deepgram, Anthropic, Groq, Cartesia, ElevenLabs, AssemblyAI) and local models (Whisper, Kokoro, Piper). LLM, STT, and TTS prices all flow through voice-prices (a fork of pydantic/genai-prices). Ships voicegw reconcile for verifying recorded numbers against provider invoices, plus per-modality cost tracking, resolver-time fallback chains, rate limiting, and a web dashboard.
Commands
# Install (editable, with dev dependencies)
pip install -e ".[dev]"
# Run tests
pytest
pytest src/voicegateway/tests/core/test_config.py # single file
pytest src/voicegateway/tests/core/test_config.py::test_name # single test
pytest --cov # with coverage
# CLI
voicegw init # create config template
voicegw serve --port 8080 # start HTTP API
voicegw dashboard # start web UI (port 9090)
voicegw status # show provider status
# Dashboard frontend (src/dashboard/frontend/)
npm install && npm run dev # dev server
npm run build # production build
# Docker
docker compose up -d # API + Dashboard
docker compose --profile local up -d # + Ollama
Architecture
Request flow: User code → Gateway.stt()/llm()/tts() → Router → Provider → Middleware pipeline (cost tracking, latency, rate limiting, fallback) → SQLite storage → Dashboard reads stored data.
Core (src/voicegateway/core/):
gateway.py— Main orchestrator, entry point for all requestsconfig.py— YAML parser with${ENV_VAR}substitutionrouter.py— Resolvesprovider/modelstrings to provider instancesregistry.py— Lazy provider factory (instantiates on first use)model_id.py— Parsesprovider/modelformat strings
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.
- 8d ago First seen · 72 lines · 1,234 tokens per session scan A dfce1c0230a5
voicegateway CLAUDE.md is an instructions file published in the GitHub repository mahimailabs/voicegateway (49 stars, last pushed 2d ago), licensed MIT. It adds 1,234 tokens to every session, about $0.0062 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.
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).
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).
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.
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.