Borrowing it
Nothing to install: this file belongs to livekit/agent-skills. 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/livekit/agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/livekit/agent-skillsWrote 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/livekit/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/livekit/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/livekit/agent-skills/agents-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.
<a href="https://agentmods.dev/instructions/livekit/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/livekit/agent-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03342 | $0.03342 |
| Opus 5.5 | $0.01337 | $0.01337 |
| Sonnet 5.5 | $0.00668 | $0.00668 |
| Haiku 4.5 | $0.00334 | $0.00334 |
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 7d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository publishes Agent Skills that teach coding agents to build, test, and ship voice agents with LiveKit. This file is for agents working in this repo, where the job is writing and evaluating skills rather than building a LiveKit agent. README.md is for the people who install the skills.
Repository map
agent-skills/
├── README.md # for users: what the skills do, how to install
├── AGENTS.md # for agents maintaining the repo (this file)
├── CONTRIBUTING.md # for human contributors: process
├── .claude-plugin/ # Claude Code marketplace + plugin manifests (see Distribution)
├── skills/ # the published skills; this layout is the install contract
│ ├── reading-livekit-docs/
│ ├── building-livekit-agents/
│ ├── debugging-livekit-agents/
│ ├── testing-livekit-agents/
│ ├── writing-livekit-scenarios/
│ │ └── references/ # scenario craft, risk coverage, connecting the agent
│ ├── running-livekit-simulations/
│ └── operating-livekit-agents/
└── evals/ # tooling for checking the skills — never under skills/
├── validate.py # structural checks on every SKILL.md
├── trigger/ # does the right skill fire for a request?
└── output/ # does following a skill produce better work?
How the skill set is meant to work
Each skill owns one job and names its siblings for adjacent jobs. Routing happens in the
description fields, which are the only part of a skill loaded before it fires. A request should
land on exactly one skill, and that skill's body should cover everything needed for its job.
| Skill | Owns | Hands off to |
|---|---|---|
| reading-livekit-docs | Looking up any LiveKit fact | — (every other skill loads it first) |
| building-livekit-agents | Architecture and voice-specific design | debugging, testing |
| debugging-livekit-agents | Live-testing during development (lk agent debugger) |
testing (to pin a bug), running (for speech issues) |
| testing-livekit-agents | Turn-level tests in pytest/Vitest | debugging (to find the bug), running (whole conversations) |
| writing-livekit-scenarios | Authoring scenarios, and the agent-side code that consumes them | running |
| running-livekit-simulations | Running simulations, CI, triage | writing (bad scenario), testing (repeat failure) |
| operating-livekit-agents | Deploying to LiveKit Cloud and running in production: worker model, prewarm, shutdown, upgrades, observability | debugging (reproduce), testing (pin), running (verify a deployed agent) |
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.
- 7d ago Changed · -18 lines · -333 tokens per session 0b85630f5ff1
- 22d ago Changed · +205 lines · +3,181 tokens per session 3fbc88d26dd5
- 1mo ago First seen · 64 lines · 494 tokens per session scan A 7ca81b0c146e
agent-skills AGENTS.md is an instructions file published in the GitHub repository livekit/agent-skills (71 stars, last pushed 7d ago), licensed MIT. It adds 3,342 tokens to every session, about $0.0134 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).