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 jjmartres/reachy-mini-sdk-skill --skill skillgit clone --depth 1 https://github.com/jjmartres/reachy-mini-sdk-skillWrote 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/jjmartres/reachy-mini-sdk-skill/skill)<a href="https://agentmods.dev/skills/jjmartres/reachy-mini-sdk-skill/skill"><img src="https://agentmods.dev/badge/skills/jjmartres/reachy-mini-sdk-skill/skill/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/jjmartres/reachy-mini-sdk-skill/skill"><img src="https://agentmods.dev/badge/skills/jjmartres/reachy-mini-sdk-skill/skill.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 | $0.00093 | $0.01929 |
| Opus 5 | $0.00046 | $0.00964 |
| Sonnet 5 | $0.00019 | $0.00386 |
| Haiku 4.5 | $0.00009 | $0.00193 |
Grade B, and why
reachy-mini-sdk 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 9d 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.
requests.post("http://localhost:8000/api/move/goto", json={ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
requests.post("http://localhost:8000/api/move/goto", json={ How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachy Mini SDK
Programming guide for Reachy Mini - an open-source desktop humanoid robot with 6-DOF head, expressive antennas, and AI integration.
Hardware
- Head: 6-DOF Stewart platform (X,Y,Z + roll,pitch,yaw)
- Antennas: 2 servos
- Body: 360° yaw rotation
- Sensors: Camera, microphone, IMU (Wireless only)
Daemon: FastAPI on port 8000 (REST + WebSocket)
Quick Start
Installation
See references/installation.md for complete setup (uv/pip, platform-specific configs, permissions).
Basic Connection
from reachy_mini import ReachyMini
# Local
with ReachyMini() as mini:
pass
# Remote (Wireless)
with ReachyMini(localhost_only=False) as mini:
pass
Movement
See references/movement_control.md for complete guide (450+ lines with all patterns).
goto_target (Smooth Interpolation)
from reachy_mini.utils import create_head_pose
import numpy as np
# create_head_pose returns a 4x4 numpy ndarray (not a HeadPose object)
mini.goto_target(
head=create_head_pose(z=10, roll=15, degrees=True, mm=True),
antennas=np.deg2rad([45, 45]),
body_yaw=np.deg2rad(30),
duration=2.0,
method="minjerk" # linear | minjerk | ease_in_out | cartoon
)
set_target (Direct Control)
For high-frequency control (>30Hz):
mini.set_target(
head=create_head_pose(z=5, mm=True),
antennas=[0.5, -0.5]
)
Coordinates
- Head: Position in meters, orientation in radians
- Antennas: Radians (±1.5)
- Body: Radians (full 360°)
Sensors
See references/sensors.md for camera, audio, IMU details.
# Camera (BGR numpy array)
frame = mini.media.get_frame()
# Audio (16kHz stereo)
samples = mini.media.get_audio_sample()
mini.media.push_audio_sample(samples) # Non-blocking
# IMU (Wireless only) - mini.imu is a property returning a dict, or None
data = mini.imu
if data is not None:
accel, gyro, quat = data["accelerometer"], data["gyroscope"], data["quaternion"]
What ships with it
11 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.
- LICENSE.txt 1.1 KB
- METADATA.yaml 3.7 KB
- references/ai_integration.md 8.7 KB
- references/api_quick_reference.md 6.5 KB
- references/daemon_api.md 11 KB
- references/daemon_operations.md 4.4 KB
- references/installation.md 4.3 KB
- references/movement_control.md 10 KB
- references/openapi_schema.json 63 KB
- references/openapi_usage.md 2.5 KB
- references/sensors.md 6.1 KB
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.
- 9d ago First seen · 253 lines · 93 tokens per session scan B e38737d611ba
reachy-mini-sdk is a skill published in the GitHub repository jjmartres/reachy-mini-sdk-skill (9 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 1,929 once invoked, about $0.0005 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
home-assistant-integration
Use this skill when creating, scaffolding, reviewing, or maintaining Python Home Assistant custom integrations, including work on customcomponents, manifests, config flows, options flows, config entries, platforms/entities, DataUpdateCoordinator, integration automation triggers, diagnostics, repairs…
document-code
Apply Google Style documentation standards to Python, Go, TypeScript, and Terraform code. Use when writing or reviewing code that needs docstrings/comments/JSDoc, when asked to "document this code", "add docstrings", "follow Google Style", or when improving code documentation quality. Supports Python docstrings, Go…
coding-guidance-python
Python implementation and review skill. Use when writing, modifying, refactoring, or reviewing Python code, especially production Python that needs clear contracts, type safety, testability, and maintainable module boundaries. Portable across Python repos and tooling stacks.
cardputer-buddy
Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to…
dask
Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed…
astropy
Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy.