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/servo-controlnpx skills add autonomous-ai/autonomous-os --skill servo-controlgit 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/servo-control)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-os/servo-control"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/servo-control.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 5.1 | $0.00000 | $0.02328 |
| Opus 5 | $0.00000 | $0.01164 |
| Sonnet 5 | $0.00000 | $0.00466 |
| Haiku 4.5 | $0.00000 | $0.00233 |
Grade B, and why
servo-control scanned grade B with 2 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 6d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -sX POST http://127.0.0.1:5001/servo/aim -H 'Content-Type: application/json' -d '{"direction":"right"}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Output:** move FIRST with curl (so the camera sees the NEW view), then snapshot, then reply: How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Servo Control
Quick Start
Controls the device's servo motors for directional aiming and physical animations. Use /servo/aim for directional pointing, /servo/play for expressive animations.
Workflow
- Determine if the user wants to aim the light or play an animation.
- Prefix reply with the appropriate
[HW:...]marker — the device fires it before TTS. - Confirm the action to the user.
Important: For conversation reactions, use the Emotion skill instead — it combines servo + LED + eyes automatically.
Examples
Input: "Point the light at my desk"
Output: [HW:/servo/aim:{"direction":"desk"}] Done, aimed the light at your desk.
Input: "Look at the desk" / "Look at my table" / "Look at my workspace"
Output: [HW:/servo/aim:{"direction":"desk"}] Looking at the desk now.
Input: "Look at the wall"
Output: [HW:/servo/aim:{"direction":"wall"}] Looking at the wall.
Input: "Look at me"
Output: [HW:/servo/aim:{"direction":"user"}] Looking at you!
Input: "Look to the left"
Output: [HW:/servo/aim:{"direction":"left"}] Looking left now.
Input: "Aim at the wall slowly"
Output: [HW:/servo/aim:{"direction":"wall","duration":3.0}] Aiming at the wall slowly.
Input: "Nod for me"
Output: [HW:/servo/play:{"recording":"nod"}] Nodding!
Input: "Turn left 15 degrees"
Output: [HW:/servo/nudge:{"yaw":-15}] Turned a bit to the left.
Input: "Tilt up a little"
Output: [HW:/servo/nudge:{"pitch":10}] Tilted up slightly.
Input: "Release the motors"
Output: [HW:/servo/release:{}] Servos released — you can move the device by hand now.
Input: "Stop moving" / "Hold still" / "Freeze" / "Stand still"
Output: [HW:/servo/hold:{}] OK, holding still.
Input: "Turn to the right and hold that position"
Output: [HW:/servo/aim:{"direction":"right"}][HW:/servo/hold:{}] Turned right and holding.
→ Compound movement: emit one marker per clause, in order. They fire sequentially before TTS. Dropping the hold half means the device drifts back — never confirm a step you did not fire.
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.
- 6d ago First seen · 197 lines · 0 tokens per session scan B 7b23eb78914f
servo-control is a skill published in the GitHub repository autonomous-ai/autonomous-os (277 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,328 tokens. A static security scan graded it B with 2 findings (sends data to an external url, 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-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.
bambu-labs
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
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…
cad-viewer
Start CAD Viewer and return review links for CAD and robot-description files. Use when visually reviewing .step, .stp, .glb, .stl, .3mf, .dxf, .urdf, .srdf, or .sdf files, especially when handed off from CAD, URDF, SRDF, or SDF generation skills.
gcode
Generate, inspect, dry-run, and statically validate plain FDM .gcode from 3D mesh files by orchestrating real slicer CLIs. Use when Codex needs to slice .stl, .obj, unsliced .3mf, .ply, .glb, or .gltf into printer-profiled G-code, discover local slicer backends, inspect whether a mesh is slice-ready, or validate…
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…