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 autonomous-ai/autonomous-os --skill faqgit clone --depth 1 https://github.com/autonomous-ai/autonomous-osWrote 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/autonomous-ai/autonomous-os/faq)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-os/faq"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/faq/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/autonomous-ai/autonomous-os/faq"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/faq.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.02936 |
| Opus 5.5 | $0.00016 | $0.01174 |
| Sonnet 5.5 | $0.00008 | $0.00587 |
| Haiku 4.5 | $0.00004 | $0.00294 |
Grade A, and why
faq 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 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.
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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Web UI FAQ
Answer questions about the UI from the controls that actually exist. Reply in the user's language. Start with the page, control, and outcome; then mention the relevant side effect. Do not invent a button, field, provider, or feature that is not described here.
First identify the context
localhost means the computer running the browser. It is not the robot.
Developing the frontend locally
The local frontend is Vite. From the repository root, run:
make web-install
LAMP_PROXY=http://<device-lan-ip> make web-dev
Open http://localhost:5173. LAMP_PROXY forwards the local UI's /api and
/hw requests, including WebSockets, to the device. Without it, Vite can show
the page shell, but Monitor and Settings cannot load or save live device data.
Using the UI already installed on a device
Open http://<device-lan-ip>/ from the same network. Use the raw LAN IP shown
by the device or router; do not guess the IP and do not present .local as the
primary address. /monitor opens the dashboard; /setting opens Settings.
The old /edit route redirects to /setting.
If the UI asks for the admin password, the user must enter it in the local UI. Never request a password, API key, bot token, or header value in chat.
Navigation and saving rules
The left sidebar has Monitor and Settings. The search field filters items by
name or group; Enter opens the first result and Esc clears it. Direct links
are relative to the current UI address, for example /setting#wifi.
Some advanced sections require the Debug toggle in the top bar. Explain what a control does before suggesting Debug; do not turn it on merely to make a user experiment with an unfamiliar setting.
Most Settings sections use the Save Changes button at the upper right. It is enabled only after an edit. A saved secret is shown as configured rather than revealed; use its edit control and enter a replacement only when changing it. Saving settings that affect voice processing can briefly restart HAL, so wait for the UI to reconnect before clicking another control.
What ships with it
1 file 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 · +1 lines f0b1e39c1c51
- 1mo ago First seen · 284 lines · 41 tokens per session scan A 66154da21f7f
faq is a skill published in the GitHub repository autonomous-ai/autonomous-os (378 stars, last pushed 18d ago), licensed Apache-2.0. It adds 41 tokens to every session and 2,936 once invoked, about $0.0002 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 skills, from other repositories
rosclaw-embodied
A set of rules for completing robot tasks in ROSClaw, a system for running and checking robot work. It covers approved robot files, acceptance evidence, and separate rules for simulation and real hardware.
default
Skill "default" from ros-claw/rosclaw, covering skill.md, skill id, intent, preconditions and effects.
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…