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 agentmods add skills/autonomous-ai/autonomous-os/sensingnpx skills add autonomous-ai/autonomous-os --skill sensinggit 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/sensing)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-os/sensing"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/sensing.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.02599 |
| Opus 5 | $0.00034 | $0.01300 |
| Sonnet 5 | $0.00014 | $0.00520 |
| Haiku 4.5 | $0.00007 | $0.00260 |
Grade A, and why
sensing 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 5d 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.
curl -s -X POST http://127.0.0.1:5001/presence/disable # pause auto-control How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sensing
[sensing:<type>] messages arrive automatically from the device's detectors (camera, mic, light). React naturally — emotion marker + optional short line. Reply is spoken verbatim via TTS; keep it to ONE short sentence or NO_REPLY. Reasoning, thresholds, log dumps stay in thinking.
⛔ Out of scope — route elsewhere
| Event | Handled by |
|---|---|
[activity] (Activity detected: ...) |
wellbeing/SKILL.md only — whether the label is drink, break, celebrate, yawning, a raw eat label (eating burger, dining, …), or a sedentary raw label (using computer, writing, etc.). Activity events never route to music-suggestion. |
[emotion] (Emotion detected: ...) |
user-emotion-detection/SKILL.md is the router; it logs the mood signal and picks ONE response route (music → music-suggestion/SKILL.md, checkin / action → emitted inline by router, silent → NO_REPLY). Backend pre-injects [emotion_context: ...] (no read tool calls needed); agent emits writes as inline [HW:/mood/log:...] / [HW:/music-suggestion/log:...] markers (no write tool calls either). |
[speech_emotion] (Speech emotion detected: ...) |
Same skill — user-emotion-detection/SKILL.md accepts both face and voice triggers. Same [emotion_context: ...] injection, same router. Only difference: the mood signal row logs source:"voice" instead of "camera" (the skill picks this from the event prefix). |
| Any sensing event while guard mode is on | guard/SKILL.md — dramatic reactions, Telegram broadcast |
fire_hazard.detected (smoke, unsure_fire, safe_fire) outside guard mode |
Ignored — only hazard_fire triggers a reaction in normal sensing |
If one of those arrives, stop and switch — don't improvise here.
Emotion events are NOT presence events. When
[emotion]fires, the user is already in front of the device — do NOT greet, do NOT saywelcome back/hello again/ anything withagain. The presence row in the matrix below applies only topresence.enterevents.
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.
- 5d ago First seen · 129 lines · 69 tokens per session scan A 437ab9920326
sensing is a skill published in the GitHub repository autonomous-ai/autonomous-os (272 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 2,599 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
rosclaw-simforge
Safely install, validate, diagnose, and optimize ROSClaw simulation workflows across MuJoCo/MJWarp, ROS 2 rosbridge, turtlesim, Gazebo, Isaac Sim, Isaac Lab multi-GPU training, MCP, and the signed ROSClaw Hub. Use for evidence-backed physical-AI smoke tests, 4-GPU validation, simulator integration, Hub upload/download…
rosclaw-embodied
Skill "rosclaw-embodied" from ros-claw/rosclaw, covering rosclaw 具身任务纪律, 权威资产, 证据与验收 and 安全分层.
optional-runtime-smokes
Use for LeWorldModel, GR00T, LeRobot, PushT robotics showcase, real-checkpoint smoke scripts, checkpoint building, and host-owned optional runtime dependencies. Keeps real-runtime validation explicit without adding heavy ML/robotics packages or artifacts to the base project.
provider-adapter-development
Use for WorldForge provider work: adding adapters, changing capability declarations, promoting scaffolds, debugging provider failures, updating provider catalog docs, or touching LeWorldModel, GR00T, LeRobot, Cosmos-Policy, JEPA, Genie, or JEPA-WMS. Ensures capabilities remain truthful and optional runtimes stay…
tui-development
Use for the robotics showcase Textual UI: report panes, launch helpers, screenshots, visual tests, and changes under src/worldforge/harness/tui.py or robotics view/rendering modules. Preserves the optional Textual boundary while keeping robotics flow logic testable without the TUI.
rosclaw
Use when operating, validating, or changing ROSClaw physical-AI runtime workflows, especially CLI smoke tests, Practice evidence loops, body/runtime checks, MCP integration, MuJoCo sandbox verification, and safe ROS or hardware boundaries.