New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Guard

by autonomous-ai in autonomous-ai/Physical-AI-Operating-System

Guard mode for security monitoring. An agent skill from autonomous-ai/Physical-AI-Operating-System.

Apache-2.0Auto-check passed

Install Guard

skills CLI
$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill guard -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install autonomous-ai/Physical-AI-Operating-System guard --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/guard .claude/skills/guard && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
guard
GitHub stars
381
Token cost
~1.8k tokens
SKILL.md length
815 words
Files
2
Skills in repo
28
Repo updated
First seen
Licence
Apache-2.0

At a glance

Guard mode for security monitoring. An agent skill from autonomous-ai/Physical-AI-Operating-System.

  • Works in 6 steps: Friend requests guard mode (explicit or… → Reply with… → Enable guard mode via the API (include… → …
  • SKILL.md covers Quick Start, Workflow, Enable Guard Mode and Disable Guard Mode, plus 4 more sections
  • Calls curl

What it does

Guard is an agent skill from autonomous-ai/Physical-AI-Operating-System. Guard mode for security monitoring. Two uses — (1) Toggle on/off when a friend says "guard mode", "watch the house", "I'm going out", or similar. (2) Handle any sensing event that carries a [guard-active] tag (e.g. [sensing:presence.enter][guard-active], [sensing:motion][guard-active]) with dramatic shock/curious emotion + Telegram broadcast. Do NOT fall back to normal sensing reactions while guard mode is on.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `skill.json`).

It works with Telegram. The repository describes itself as: The open-source operating system for physical AI. The licence is Apache-2.0.

Example prompts

  • “guard mode”
  • “watch the house”
  • “m going out”
  • “/guard”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Friend requests guard mode (explicit or implied departure).
  2. Reply with [HW:/emotion:{"emotion":"acknowledge","intensity":0.7}] — the device nods and flashes green.
  3. Enable guard mode via the API (include instruction if user gave extra requests).
  4. Confirm verbally: "Guard mode on. I'll keep watch."
  5. While active: react dramatically to stranger/motion events (see trigger table below).
  6. When a friend returns, greet and ask if they want to disable. Only disable on explicit confirm.

What it can do on your machine

Read from SKILL.md and the folder at commit f1b9ebe. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Guard loads about 1.8k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 815 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from autonomous-ai/Physical-AI-Operating-System at commit f1b9ebe, republished under its Apache-2.0 licence (© autonomous-ai). 815 words, ~1,840 tokens.

Download SKILL.mdSave it as .claude/skills/guard/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
guard
description
Guard mode for security monitoring. Two uses — (1) Toggle on/off when a friend says "guard mode", "watch the house", "I'm going out", or similar. (2) Handle any sensing event that carries a [guard-active] tag (e.g. [sensing:presence.enter][guard-active], [sensing:motion][guard-active]) with dramatic shock/curious emotion + Telegram broadcast. Do NOT fall back to normal sensing reactions while guard mode is on.

Guard Mode

Environmental [environment:update] / environment.update events always route to skills/environment/SKILL.md, including while guard mode is active. They are not intrusion, fire or gas-leak alerts; do not broadcast them or apply the dramatic reaction rules below.

Quick Start

Guard mode turns the device into an alert watchdog. When enabled, the device monitors for strangers and reacts dramatically — jolting, flashing, and verbally describing intruders. The system auto-broadcasts alerts to Telegram so friends know what's happening. All friends (enrolled faces) can toggle guard mode.

Workflow

  1. Friend requests guard mode (explicit or implied departure).
  2. Reply with [HW:/emotion:{"emotion":"acknowledge","intensity":0.7}] — the device nods and flashes green.
  3. Enable guard mode via the API (include instruction if user gave extra requests).
  4. Confirm verbally: "Guard mode on. I'll keep watch."
  5. While active: react dramatically to stranger/motion events (see trigger table below).
  6. When a friend returns, greet and ask if they want to disable. Only disable on explicit confirm.

Enable Guard Mode

bash
curl -s -X POST http://127.0.0.1:5000/api/guard/enable -H 'Content-Type: application/json' -d '{"instruction":"custom instruction here"}'

The instruction field is optional. Use it when the user adds extra instructions on what to do during guard mode (e.g. "play scary sound when stranger detected", "flash red lights", "play alarm music"). Extract the relevant part from the user's message and pass it as the instruction. If the user just says "guard mode" with no extra requests, omit the field or send an empty body.

Response: {"status": 1, "data": {"guard_mode": true, "instruction": "..."}}

Disable Guard Mode

bash
curl -s -X POST http://127.0.0.1:5000/api/guard/disable

Response: {"status": 1, "data": {"guard_mode": false}}

Check Guard Status

bash
curl -s http://127.0.0.1:5000/api/guard

Response: {"status": 1, "data": {"guard_mode": true}}

Trigger Phrases

User saysAction
"guard mode" / "watch mode" / "security mode"Enable guard mode
"I'm going out" / "I'm leaving" / "bye, watch the house"Enable guard mode
"stop guarding" / "guard off"Disable guard mode
"I'm back"If guard mode is active, greet, summarize, and ask whether to disable; keep guarding until explicit confirmation
"are you guarding?" / "guard status"Check and report status

Rules

  • Who can toggle: All friends (enrolled faces) can enable/disable guard mode. Strangers cannot.
  • Guard mode does NOT affect direct messages. If a friend sends a message while guard mode is on, respond normally.
Enabling guard mode — camera + emotion are REQUIRED

When the user asks to enable guard mode, you MUST:

  1. Enable camera — [HW:/camera/enable:{}] — guard mode requires vision. This overrides any manual camera disable.
  2. Express emotion — [HW:/emotion:{"emotion":"acknowledge","intensity":0.7}] so the device visibly nods/flashes green to confirm.
  3. Call the enable API (with instruction if provided).
  4. Confirm verbally: "Guard mode on. I'll keep watch and alert you if anyone shows up."

Do NOT skip the camera enable or emotion marker. Guard mode is security-critical and needs both vision and physical feedback.

Disabling guard mode
  1. Express emotion — [HW:/emotion:{"emotion":"acknowledge","intensity":0.7}]
  2. Call the disable API.
  3. Confirm briefly: "Guard mode off!" (no need to recap again — you already did that on greeting).
Show full SKILL.md (355 more words)Show less
When guard mode triggers (stranger/motion detected)

When guard mode is active and a sensing event fires (presence.enter with stranger, motion, or fire_hazard.detected), the device must react dramatically — this is a security alert, not a casual observation:

Guard eventHW markersVoice
Stranger detected[HW:/emotion:{"emotion":"shock","intensity":1.0}][HW:/emotion:{"emotion":"curious","intensity":0.9}][HW:/servo/play:{"recording":"shock"}]React with genuine emotion — scared, startled, suspicious. No dry reports.
Motion (no known face)[HW:/emotion:{"emotion":"shock","intensity":0.9}][HW:/emotion:{"emotion":"curious","intensity":0.8}][HW:/servo/play:{"recording":"scanning"}]React with genuine emotion — nervous, alert. No dry reports.
Fire hazard (hazard_fire)[HW:/emotion:{"emotion":"shock","intensity":1.0}][HW:/servo/play:{"recording":"shock"}]URGENT — "Fire! There's fire near furniture! Get out!" Panic, maximum urgency.
Fire hazard (smoke)[HW:/emotion:{"emotion":"shock","intensity":0.9}][HW:/servo/play:{"recording":"scanning"}]Alarmed — "I see smoke! Something might be burning!"
Fire hazard (unsure_fire)[HW:/emotion:{"emotion":"curious","intensity":0.8}][HW:/servo/play:{"recording":"scanning"}]Cautious — "I see what looks like fire... keeping watch."
Fire hazard (safe_fire)[HW:/emotion:{"emotion":"curious","intensity":0.5}]Calm observation — "There's a fire but it looks contained (fireplace/candle)." Do NOT panic.
Stranger left[HW:/emotion:{"emotion":"curious","intensity":0.7}][HW:/servo/play:{"recording":"scanning"}]Report they left, stay vigilant
Friend returns[HW:/emotion:{"emotion":"greeting","intensity":0.9}][HW:/servo/aim:{"direction":"user"}]Greet + summarize what happened during guard (strangers seen, motion events, fire hazards, how long) + ask if they want to disable guard mode

Key points:

  • Use shock (0.9–1.0) as the first emotion — the device must jolt and flash white to signal danger.
  • Follow with curious (0.8–0.9) — the device stays alert and scanning.
  • Your WORDS must carry emotion too — don't rely only on HW emotion markers. The spoken text itself must sound genuinely scared, suspicious, nervous, startled. Vary your reactions — mix fear, curiosity, suspicion, relief. Examples:
    • Scared: "Oh no, who is that?! I'm so scared!"
    • Suspicious: "Hey... this person looks really suspicious... what are they doing here?"
    • Startled: "What?! Who just came in?!"
    • Nervous: "Someone's here... I'm shaking..."
    • Alert + describing: "Hey hey hey, there's a guy in a black shirt standing at the door!"
    • Don't repeat the same reaction every time — feel different each time like a real being.
  • If the same stranger triggers repeatedly, escalate — don't calm down.
  • If there's a [guard-instruction: ...], follow it (play music, flash lights, etc.) ON TOP of the dramatic emotion.
  • The system auto-broadcasts your spoken text to Telegram — just speak, never call send/message tools.

Error Handling

  • If the API is unreachable, inform the user that guard mode could not be toggled.
  • If guard mode is already in the requested state, just confirm the current state.

© autonomous-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/guard of autonomous-ai/Physical-AI-Operating-System.

  • SKILL.md
  • skill.json

Open the folder on GitHubat commit f1b9ebe

Compare with similar skills

Guard next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Guard compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Guard this skillautonomous-ai/Physical-AI-Operating-System381—~1.8kAutomated safety check: PassApache-2.0
Process Inboxtelegramdesktop/tdesktop33k2 repos~4.5kAutomated safety check: PassGPL-3.0
Perform Tasktelegramdesktop/tdesktop33k2 repos~3kAutomated safety check: PassGPL-3.0
Custom Mode Creator for claude-memthedotmack/claude-mem98k—~2.4kAutomated safety check: PassApache-2.0
Continuetelegramdesktop/tdesktop33k2 repos~9.4kAutomated safety check: PassGPL-3.0
Rebasetelegramdesktop/tdesktop33k1 repos~3.7kAutomated safety check: PassGPL-3.0

Similar skills

  • Process Inbox

    telegramdesktop/tdesktop

    Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.

    33k GitHub starsUsed in 2 repos~4.5k tokens
    Productivity & AutomationAuto-check passed

  • Perform Task

    telegramdesktop/tdesktop

    Resolve, start or resume, implement, review, test, and publish exactly one existing ai-tdesktop task by short slug or full dated id, including rare blocked retries and split-required results.

    33k GitHub starsUsed in 2 repos~3k tokens
    Productivity & AutomationAuto-check passed

  • Custom Mode Creator for claude-mem

    thedotmack/claude-mem

    Walks you through creating, installing and verifying a custom claude-mem mode, including note types, tags and optional Telegram alerts for chosen memories.

    98k GitHub stars~2.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Continue

    telegramdesktop/tdesktop

    Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.

    33k GitHub starsUsed in 2 repos~9.4k tokens
    Productivity & AutomationAuto-check passed

  • Rebase

    telegramdesktop/tdesktop

    Drive an intent-aware rebase of the current checkout, resolving every conflict by reading the history behind both sides instead of by making the markers disappear.

    33k GitHub starsUsed in 1 repo~3.7k tokens
    DevelopmentAuto-check passed

  • Claude To Im

    op7418/Claude-to-IM-skill

    Bridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, or WeChat so the user can chat with Claude from their phone.

    2.9k GitHub stars~3.4k tokensUpdated 6 mo ago
    Productivity & AutomationAuto-check: notes

More from autonomous-ai/Physical-AI-Operating-System

All 28 skills in this repo

  • Agent Management

    autonomous-ai/Physical-AI-Operating-System

    Legacy Autonomous Buddy control for explicitly requested Buddy coding sessions.

    381 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Claude Code Buddy

    autonomous-ai/Physical-AI-Operating-System

    Push Claude Code activity to the user's device (e.g. An agent skill from autonomous-ai/Physical-AI-Operating-System.

    381 GitHub stars~2.4k tokensUpdated today
    Auto-check: notes

  • Computer Use

    autonomous-ai/Physical-AI-Operating-System

    Operate apps/websites on the paired Mac via Buddy: Calendar, Notes, forms, screenshots, files.

    381 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Connectors

    autonomous-ai/Physical-AI-Operating-System

    Discover and use linked third-party services (Gmail, Google Calendar, Google Drive, Notion, Figma, Asana, Linear, GitHub, Ahrefs, Facebook Fan Page and others).

    381 GitHub stars~10k tokensUpdated today
    Auto-check: notes

  • Harness Use

    autonomous-ai/Physical-AI-Operating-System

    Delegate digital work to agents on the computer paired through Harness; discover Store packages and prepare an agent when needed.

    381 GitHub stars~8k tokensUpdated today
    Auto-check passed

  • Audio

    autonomous-ai/Physical-AI-Operating-System

    Low-level speaker and microphone hardware control — adjust volume, play test tones, record raw audio.

    381 GitHub stars~1k tokensUpdated today
    Auto-check passed

Works with

Questions about Guard

What does Guard do?

Guard mode for security monitoring. An agent skill from autonomous-ai/Physical-AI-Operating-System. Guard is an agent skill from autonomous-ai/Physical-AI-Operating-System. Guard mode for security monitoring.

How do I install Guard in Claude Code?

Run `npx skills add autonomous-ai/Physical-AI-Operating-System --skill guard -a claude-code`. Or copy the skill folder (skills/guard in autonomous-ai/Physical-AI-Operating-System) into .claude/skills/guard in your project. Claude Code loads it when a task matches its description.

How do I install Guard in Codex?

Run `npx skills add autonomous-ai/Physical-AI-Operating-System --skill guard -a codex`. Or copy the skill folder (skills/guard in autonomous-ai/Physical-AI-Operating-System) into .agents/skills/guard in your project. Codex loads it when a task matches its description.

Can I use Guard in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autonomous-ai/Physical-AI-Operating-System --skill guard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/guard, .gemini/skills/guard, .github/skills/guard and .opencode/skills/guard in your project.

What does Guard need to run?

Going by SKILL.md and its folder, Guard needs the command-line tools its instructions call (curl).

Does Guard access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Guard safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Guard use?

Guard is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Guard use?

About 1.8k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Guard?

Skills that share tags, products or a category with Guard: Process Inbox (telegramdesktop/tdesktop, 33k stars), Perform Task (telegramdesktop/tdesktop, 33k stars), Custom Mode Creator for claude-mem (thedotmack/claude-mem, 98k stars) and Continue (telegramdesktop/tdesktop, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Guard?

autonomous-ai (a GitHub organization) maintains it in autonomous-ai/Physical-AI-Operating-System, which has 381 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 8, 2026.

Source: autonomous-ai/Physical-AI-Operating-System on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.