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 environmentgit 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/environment)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-os/environment"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/environment/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/environment"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/environment.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 | $0.04020 |
| Opus 5.5 | $0.00044 | $0.01608 |
| Sonnet 5.5 | $0.00022 | $0.00804 |
| Haiku 4.5 | $0.00011 | $0.00402 |
Grade A, and why
environment 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.
curl --fail --silent --show-error --max-time 5 http://127.0.0.1:5000/api/environment/status How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Environment
Scope and data
Work from the device's declared environment capability and the measurements actually present. Do not require a camera, microphone, emotion marker, or a particular sensor model. If the capability is absent, skip environmental checks; ordinary room questions and room-feeling reports use the fixed unavailable reply in reference/room-comfort.md. Personal symptoms without a room question retain wellbeing support without sensor-error commentary. Do not enable hardware or edit its declaration.
For a direct room question or room-feeling report (even without a question), a requested current comparison, or a non-urgent wellbeing concern when the capability is declared, read the OS environment status API once (reuse a supplied current status snapshot when available):
curl --fail --silent --show-error --max-time 5 http://127.0.0.1:5000/api/environment/status
This read-only route admits local device callers and checks the environment capability. It returns the OS envelope {"status":1,"data":{...HAL snapshot...},"message":null}; inspect data. A non-2xx response or status:0 means unavailable. Do not bypass a denial through HAL or fetch credentials for the browser's authenticated hardware proxy.
Use the existing snapshot in an automatic event unless it is stale or the user explicitly requests a fresh check. Do not run a polling loop, start a cron job, invent a history endpoint, or promise a timed follow-up: OS owns polling, thresholds, sustained-change detection and cooldowns.
A usable snapshot has enabled: true, state: "ready", stale: false, and at least one fresh numeric measurement in sample. The shared status sample always contains nine nullable metric keys; an object of null values is not usable data. Check age_s and sample.timestamp before describing it as current. Disabled, starting, stopped, error, missing or stale data is unavailable, not zero pollution. Say so briefly on an explicit room-data question; stay silent on an unusable automatic event. For a personal wellbeing concern without a room question, silently skip unavailable environmental data and continue support without sensor-error commentary. Ordinary room questions/reports use the unavailable reply in reference/room-comfort.md. Individual null or absent measurements are unknown: retain the other valid readings. For a multi-component snapshot, sources[metric] identifies its entry in components; check that component's state, age and stale flag, plus metric_timestamps[metric]. The aggregate timestamp may belong to another sensor and does not establish freshness for every field. One failed component does not invalidate another healthy component.
What ships with it
2 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 · +28 lines · +13 tokens per session 2bba41eec366
- 1mo ago Changed · +22 lines · +4 tokens per session ff378e01d055
- 1mo ago Changed · +32 lines · +9 tokens per session a6c45e68a69c
- 1mo ago First seen · 99 lines · 83 tokens per session scan A ea56a96fb066
environment is a skill published in the GitHub repository autonomous-ai/autonomous-os (378 stars, last pushed 22d ago), licensed Apache-2.0. It adds 109 tokens to every session and 4,020 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 2026-09-12.
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.
srdf
MoveIt2 SRDF authoring, validation, and planning-semantics workflow. Use when creating, editing, inspecting, or validating .srdf files, MoveIt planning groups, virtual joints, passive joints, end effectors, group states, disabled collisions, URDF-paired planning semantics, or SRDF handoff for live review. Use the URDF…
urdf
URDF robot description authoring and validation. Use when creating, editing, inspecting, validating, or debugging .urdf files, robot links, joints, limits, inertials, visual/collision geometry, mesh references, frame conventions, or robot-description artifacts. Use the SRDF skill for MoveIt2 semantic groups and…
step-parts
Find, evaluate, and download common purchasable CAD parts from step.parts, including named off-the-shelf actuators, servos, motors, electronics boards, connectors, screws, bolts, nuts, washers, bearings, standoffs, and other catalog components. Use when Codex needs to search the hosted step.parts catalog before…
gcode
Slice 3D models into printer-ready G-code with OrcaSlicer, the open-source slicer with built-in profiles for most FDM printers (Prusa, Bambu Lab, Creality, Voron and more). Use when the user wants an .stl, .3mf or .obj model sliced for their printer, as a sliced .gcode.3mf or plain .gcode, headless with OrcaSlicer's…
sendcutsend
Review DXF and STEP/STP uploads for SendCutSend.com orders using its ordering guide, catalog, and specs. Use only for SendCutSend.com preflight reports covering upload readiness, selected material/SKU/thickness/service availability, and service-specific checks for laser cutting, CNC routing, bending, tapping…