clawatar

A web-based 3D avatar viewer that gives an AI agent a visible character using VRM models, a file format for animated 3D avatars. It supports animations, facial expressions, voice playback, and lip syncing, and can be controlled over a local WebSocket connection.

In plain words
What is it for?
Use it to build an avatar companion, VTuber-style character, or visual agent that can wave, change expression, speak, and match mouth movement to speech.
Why use it?
It provides a visual body and conversational presentation for an agent instead of limiting interaction to text or a plain interface. You must supply the VRM model yourself.

Skill for Claude CodeCodex

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 skills/dongping-chen/clawatar/skill
Any agent
npx skills add Dongping-Chen/Clawatar --skill skill
Clone the repo
git clone --depth 1 https://github.com/Dongping-Chen/Clawatar

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 881 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00071 $0.00881
Opus 5 $0.00036 $0.00441
Sonnet 5 $0.00014 $0.00176
Haiku 4.5 $0.00007 $0.00088

Measured 3d ago against content hash 60a88e044c84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clawatar 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 3d 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.

skill/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clawatar — 3D VRM Avatar Viewer

Give your AI agent a body. Web-based VRM avatar with 162 animations, expressions, TTS lip sync, and AI chat.

Transport note: ws://127.0.0.1:8765 in this skill is for local web viewer control/dev only. Apple clients (iPhone/iPad/macOS) use relay-only transport.

Install & Start

# Clone and install
git clone https://github.com/Dongping-Chen/Clawatar.git ~/.openclaw/workspace/clawatar
cd ~/.openclaw/workspace/clawatar && npm install

# Start (Vite + WebSocket server)
npm run start

Opens at http://localhost:3000 with WS control at ws://127.0.0.1:8765.

Users must provide their own VRM model (drag & drop onto page, or set model.url in clawatar.config.json).

WebSocket Commands

Send JSON to ws://127.0.0.1:8765:

play_action

{"type": "play_action", "action_id": "161_Waving"}

set_expression

{"type": "set_expression", "name": "happy", "weight": 0.8}

Expressions: happy, angry, sad, surprised, relaxed

speak (requires ElevenLabs API key)

{"type": "speak", "text": "Hello!", "action_id": "161_Waving", "expression": "happy"}

reset

{"type": "reset"}

Quick Animation Reference

Mood Action ID
Greeting 161_Waving
Happy 116_Happy Hand Gesture
Thinking 88_Thinking
Agreeing 118_Head Nod Yes
Disagreeing 144_Shaking Head No
Laughing 125_Laughing
Sad 142_Sad Idle
Dancing 105_Dancing, 143_Samba Dancing, 164_Ymca Dance
Thumbs Up 153_Standing Thumbs Up
Idle 119_Idle

Full list: public/animations/catalog.json (162 animations)

Sending Commands from Agent

cd ~/.openclaw/workspace/clawatar && node -e "
const W=require('ws'),s=new W('ws://127.0.0.1:8765');
s.on('open',()=>{s.send(JSON.stringify({type:'speak',text:'Hello!',action_id:'161_Waving',expression:'happy'}));setTimeout(()=>s.close(),1000)})
"

UI Features

  • Touch reactions: Click avatar head/body for reactions
  • Emotion bar: Quick 😊😢😠😮😌💃 buttons
  • Background scenes: Sakura Garden, Night Sky, Café, Sunset
  • Camera presets: Face, Portrait, Full Body, Cinematic
  • Voice chat: Mic input → AI response → TTS lip sync

Read the full file on GitHub · 95 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. 3d ago First seen · 95 lines · 71 tokens per session scan A 60a88e044c84

Subscribe to this mod's changes

clawatar is a skill published in the GitHub repository Dongping-Chen/Clawatar (22 stars, last pushed 6mo ago), licensed MIT. It adds 71 tokens to every session and 881 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens