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 automateyournetwork/netclaw --skill tavus-palgit clone --depth 1 https://github.com/automateyournetwork/netclawWrote 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/automateyournetwork/netclaw/tavus-pal)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/tavus-pal"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/tavus-pal/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/automateyournetwork/netclaw/tavus-pal"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/tavus-pal.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 | $0.00036 | $0.00350 |
| Opus 5.5 | $0.00014 | $0.00140 |
| Sonnet 5.5 | $0.00007 | $0.00070 |
| Haiku 4.5 | $0.00004 | $0.00035 |
Grade A, and why
tavus-pal 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 10d 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.
What it actually says
Tavus Pal
Use the setup guide for commands and deployment checks. The first implementation explains concepts through an isolated NetClaw agent with all tools denied. It does not provide device access or the main agent's memory.
- The HUD calls the local stdio
pal_query(question, session_id)facade. Its results stay local until the operator selects Speak this answer. Do not send raw results through Tavus events or reinterpret tool output as approval. - Free uses stock video faces. A locally selected smiley/lobster is only a browser icon; do not describe it as a custom Tavus avatar. Custom image training is not part of this free workflow.
status,facesandverifydo not create conversations. Provisioning creates a PAL and tool, not a call. The API key alone never enables Pal.- Confirm current allowance before starting. A lost create/end response consumes its reservation and blocks another start. Use Reconcile; do not reset the ledger, create another PAL or retry a mutation blindly to regain minutes.
- A gateway/policy failure means unavailable, not a device-health finding. GAIT failure prevents new dispatch; call cleanup must remain possible.
Never upgrade, train a custom face, publish a listener or contact other people as a side effect of setup. Honor existing session authorization for the requested local setup and keep incomplete live acceptance visible.
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.
- 10d ago First seen · 29 lines · 36 tokens per session scan A 9a3c97573d1a
tavus-pal is a skill published in the GitHub repository automateyournetwork/netclaw (684 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 350 once invoked, about $0.0001 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 2026-10-10.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…