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/runwayml/avatars-sdk-react/agents-mdgit clone --depth 1 https://github.com/runwayml/avatars-sdk-reactWhat 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 | $0.01385 | $0.01385 |
| Opus 5 | $0.00692 | $0.00692 |
| Sonnet 5 | $0.00277 | $0.00277 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
avatars-sdk-react 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines
Context for AI agents working with the Runway Avatar SDK monorepo.
Repository Structure
packages/
core/ → @runwayml/avatars (framework-agnostic)
react/ → @runwayml/avatars-react (React bindings)
examples/
vanilla-js/ Pure JS demo
nextjs-simple/ Minimal Next.js
nextjs/ Full Next.js with presets
nextjs-client-events/ Client event tools
express/ Express + Vite
...
docs/ Reference docs (holding files)
Package Architecture
Core (packages/core/) — No React, no framework dependency. LiveKit is the only runtime dep but fully abstracted from the public API.
src/
├── client.ts # AvatarSession class + streamTo/connect entry points
├── emitter.ts # Tiny typed event emitter
├── transcript-accumulator.ts
├── types.ts # All shared types + AvatarEvent enum
├── tools.ts # clientTool / Standard Schema
├── standard-schema.ts
├── api/
│ ├── consume.ts # consumeSession HTTP call
│ ├── config.ts # DEFAULT_BASE_URL
│ ├── page-actions.ts # Page action tool definitions
│ └── index.ts # /api subpath entry
└── utils/
├── parseClientEvent.ts
├── parseTranscription.ts
└── flatDeltaAccumulator.ts
React (packages/react/) — Components and hooks. Depends on @runwayml/avatars as a regular dependency. No direct LiveKit imports.
src/
├── components/ # AvatarCall, AvatarProvider, AvatarSession, AvatarVideo, etc.
├── hooks/ # useAvatarSession, useAvatar, useLocalMedia, useTranscript, etc.
├── api/index.ts # Re-exports from core /api for backwards compat
├── types.ts # React-specific types (props, context values)
├── styles.css
└── index.ts
Key Patterns
Core SDK API:
const session = await streamTo({ credentials, target: videoEl });
session.mic.toggle();
session.on(AvatarEvent.AvatarVideoReady, (track) => { ... });
session.end();
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.
- 2d ago First seen · 126 lines · 1,385 tokens per session scan A f66f59b2509c
avatars-sdk-react AGENTS.md is an instructions file published in the GitHub repository runwayml/avatars-sdk-react (22 stars, last pushed 15d ago), licensed MIT. It adds 1,385 tokens to every session, about $0.0069 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
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.
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).
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.