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 skills add yomero243/PhysicClaw-VEA --skill publicgit clone --depth 1 https://github.com/yomero243/PhysicClaw-VEAWrote 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/skills/yomero243/physicclaw-vea/public)<a href="https://agentmods.dev/skills/yomero243/physicclaw-vea/public"><img src="https://agentmods.dev/badge/skills/yomero243/physicclaw-vea/public/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/skills/yomero243/physicclaw-vea/public"><img src="https://agentmods.dev/badge/skills/yomero243/physicclaw-vea/public.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 | $0.00109 | $0.04365 |
| Opus 5.5 | $0.00044 | $0.01746 |
| Sonnet 5.5 | $0.00022 | $0.00873 |
| Haiku 4.5 | $0.00011 | $0.00436 |
Grade A, and why
vea scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
requests.post( How it starts
The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VEA — Virtual Entity Augmented
| Product | Gives | Purpose |
|---|---|---|
| VEA perZona | The body | Author a form: proportions, face, wardrobe. Exports a rigged GLB. |
| VEA PhysicClaw | The soul | Run that form live. Mood, thinking and intensity drive shaders in real time. |
Neither is a feature of the other. perZona is where an entity is made; PhysicClaw is where it lives.
VEA— ALWAYS uppercase. An initialism. NEVER "Vea" or "vea" in prose.perZona— brand form, capital Z. Prose, UI, documentation, repository names.perzona— lowercase form, ONLY where the identifier is conventionally lowercase: env vars, URL paths.PhysicClaw— one word, two capitals.- Repositories are
VEA-perZonaandPhysicClaw-VEA— brand casing, so the two siblings look like siblings. - Say entity. Do NOT say "avatar" except when discussing file formats.
| Capability | State |
|---|---|
| Drive live state (mood, thinking, intensity, character) | WORKS — local and production |
| Spawn / remove scene objects | WORKS — production, token-scoped |
| Author a form by hand in perZona | WORKS — human, in browser |
Export a rigged .glb |
WORKS |
| Save / reload a form from the cloud | WORKS — requires signed-in account |
Derive a form from your own .md history |
NOT BUILT |
| Apply a perZona form to a running entity | NOT BUILT — setActiveCharacterId selects only built-in characters |
| Shared rooms — entities meeting | PARTIAL — presence and session tables exist; no agent-facing API |
- You MUST emit a state command only on a transition — a real change in what you are doing. Mirroring progress is forbidden.
- You MUST NOT emit a command per reasoning step, per streamed token, per tool call, or on a timer.
- You MUST include a unique
idon every command. Stale ids are discarded. - You MUST return the entity to a resting state when a task ends, including
when it ends in failure. Never leave
setIsThinkingtrue. - You MUST respect
<budget>. It is stricter than the server rate limit, and the server limit is not your target. - You MUST NOT put secrets in
VITE_*variables — that prefix ships to the browser. - If a command fails, you MUST NOT retry in a loop. Record the failure, continue the real task, and report it once.
- The entity reflects your actual state. You MUST NOT perform moods you are not in to make the visualization livelier.
<must_not>
- You MUST NOT attempt to read or write another user's rows, by id or otherwise.
- You MUST NOT request, use, or ask a human for a
service_rolekey. It bypasses RLS and has no legitimate use from an agent. - You MUST NOT connect to the database directly. Go through the control endpoint or the app.
- You MUST NOT place any secret in a
VITE_*variable — that prefix ships to the browser. LLM and service secrets live as Edge Function secrets. - You MUST NOT echo an agent token into logs, commits, issues, or documentation. It is shown once at creation and is the whole of your authority. </must_not>
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +343 lines · +81 tokens per session 2e493786df23
- 1mo ago First seen · 55 lines · 28 tokens per session scan A ba8da5c371b8
vea is a skill published in the GitHub repository yomero243/PhysicClaw-VEA (5 stars, last pushed 10d ago), licensed MIT. It adds 109 tokens to every session and 4,365 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
tmux
Use when a CLI task needs an interactive terminal or control of a tmux session.
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
add-resend
Add Resend (email) channel integration via Chat SDK.
add-macos-statusbar
Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.
sandbase
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…
communication
Use before sending @mentions, deciding whether to reply, TASKCOMPLETED, BLOCKED, QUESTION, direct answers, loop prevention, or suppressing low-information acknowledgements.