agentmods.dev

local-livekit-plugins: Instructions file for Claude Code

CLAUDE.md

local-livekit-plugins CLAUDE.md is an instructions file for Claude Code from CoreWorxLab/local-livekit-plugins. It costs 303 tokens per session, scanned A, original, MIT.

Project instructions for local LiveKit plugins that provide speech-to-text and text-to-speech without cloud APIs. They describe the package structure, important import rules, hardware notes, and development commands.

In plain words
What is it for?
Use them when developing, running, linting, type-checking, or testing the local faster-whisper speech-recognition and Piper speech-synthesis plugins.
Why use it?
They give a coding agent the project context needed to change or test these plugins without guessing how the repository works.

Instructions file for Claude Code

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

This is CoreWorxLab/local-livekit-plugins's own configuration. It tells Claude Code how to work on local-livekit-plugins 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 local-livekit-plugins configures →

not rated 65repo +1 11mo ago A scan 303 tokens original MIT
View source ↗ CoreWorxLab/local-livekit-plugins
Reuse

Borrowing it

Nothing to install: this file belongs to CoreWorxLab/local-livekit-plugins. 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/CoreWorxLab/local-livekit-plugins/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/CoreWorxLab/local-livekit-plugins

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 local-livekit-plugins CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/coreworxlab/local-livekit-plugins/claude-md/github.svg)](https://agentmods.dev/instructions/coreworxlab/local-livekit-plugins/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/coreworxlab/local-livekit-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/coreworxlab/local-livekit-plugins/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.

agentmods 80×15 button for local-livekit-plugins CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/coreworxlab/local-livekit-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/coreworxlab/local-livekit-plugins/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 303 This file is loaded in full into every session.
When invoked 303 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00303 $0.00303
Opus 5.5 $0.00121 $0.00121
Sonnet 5.5 $0.00061 $0.00061
Haiku 4.5 $0.00030 $0.00030

Measured 2mo ago against content hash 87ec2955fd4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-livekit-plugins 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 2mo 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 · 34 lines

What it actually says

CLAUDE.md

Project Overview

LiveKit Local Plugins - Custom STT and TTS plugins for LiveKit Agents that run entirely locally without cloud APIs.

Architecture

  • src/local_livekit_plugins/ - The installable Python package
    • faster_whisper_stt.py - STT plugin using faster-whisper (GPU-accelerated)
    • piper_tts.py - TTS plugin using Piper
  • examples/ - Demo code showing how to use the plugins (not part of installed package)

Key Technical Notes

  • Plugin imports must be at module level - LiveKit requires plugins to be registered on the main thread. Never import plugins inside functions.
  • PyTorch provides CUDA libraries - torch dependency bundles nvidia-cublas-cu12 etc. for faster-whisper GPU support
  • Piper CUDA has version constraints - CPU mode (use_cuda=False) is recommended due to CUDA 12+ compatibility issues

Development Commands

uv sync                              # Install dependencies
uv run examples/voice_agent.py dev   # Run with LiveKit playground
uv run examples/voice_agent.py console  # Run in console mode
uv run ruff check src/               # Lint
uv run mypy src/                     # Type check
uv run pytest                        # Test

Environment

Requires .env.local in examples/ directory (copy from .env.local.example).

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. 2mo ago First seen · 34 lines · 303 tokens per session scan A 87ec2955fd4c

Subscribe to this mod's changes

local-livekit-plugins CLAUDE.md is an instructions file published in the GitHub repository CoreWorxLab/local-livekit-plugins (65 stars, last pushed 11mo ago), licensed MIT. It adds 303 tokens to every session, about $0.0012 per session on Opus 5.5. 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.

Related

local-livekit-plugins CLAUDE.md compared with instructions from other repositories

local-livekit-plugins CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
local-livekit-plugins CLAUDE.mdCoreWorxLab/local-livekit-pluginsInstructions file6511mo agoMITA303Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot