agent-skills AGENTS.md

A set of repository instructions for the LiveKit agent-skills project, including its folder structure, contribution rules, and skill-file format.

In plain words
What is it for?
Use it when working on LiveKit agent skills, especially when adding or editing SKILL.md files, checking repository structure, or preparing contributions.
Why use it?
It gives coding agents the project-specific rules they need before changing files. This helps prevent invalid skill files and changes that conflict with the repository's conventions.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/livekit/agent-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/livekit/agent-skills

Made for: Codex, OpenCode.

Per session 494 This file is loaded in full into every session.
When invoked 494 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00494 $0.00494
Opus 5 $0.00247 $0.00247
Sonnet 5 $0.00099 $0.00099
Haiku 4.5 $0.00049 $0.00049

Measured 2d ago against content hash 7ca81b0c146e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-skills AGENTS.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 2d 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.

AGENTS.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repository contains AI agent skills for building with LiveKit. The skills follow the Agent Skills format.

Repository Structure

agent-skills/
├── README.md           # User-facing documentation
├── AGENTS.md           # This file (for AI agents)
├── CLAUDE.md           # Points to AGENTS.md
└── skills/
    ├── livekit-agents/         # LiveKit Agents skill
    │   ├── SKILL.md            # The skill content
    │   └── references/         # Supporting documentation
    └── livekit-simulations/    # LiveKit Simulations skill
        ├── SKILL.md            # The skill content
        ├── references/         # Supporting documentation
        └── scripts/            # Supporting scripts

Contributing Guidelines

Skill Content Principles

All skills in this repository must follow the "freeze forever" principle:

  1. Encode behavior, not knowledge - Skills teach how to approach problems, not API specifics
  2. Direct to MCP for facts - All factual information must come from live documentation
  3. Require testing - Every agent implementation must include tests
  4. Stay under 500 lines - Keep skills concise for context efficiency

SKILL.md Format

Each skill requires YAML frontmatter:

---
name: skill-name-kebab-case
description: Trigger phrases and brief description. Include phrases like "build a voice agent" that help agents recognize when to use this skill.
license: MIT
metadata:
  author: livekit
  version: "X.Y.Z"
---

File Naming

  • Skill directories use kebab-case
  • SKILL.md is the only uppercase filename
  • Supporting docs go in references/ subdirectory

LiveKit MCP Server

These skills are designed to work with the LiveKit Docs MCP server. If you're working on this repository and need to test MCP integration, make sure it is installed. Installation instructions are available at https://docs.livekit.io/intro/mcp-server/

Read the full file on GitHub · 64 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. 2d ago First seen · 64 lines · 494 tokens per session scan A 7ca81b0c146e

Subscribe to this mod's changes

agent-skills AGENTS.md is an instructions file published in the GitHub repository livekit/agent-skills (66 stars, last pushed 2mo ago), licensed MIT. It adds 494 tokens to every session, about $0.0025 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.