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 sandraschi/yahboom-mcp --skill yahboom-operatorgit clone --depth 1 https://github.com/sandraschi/yahboom-mcpWrote 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/sandraschi/yahboom-mcp/yahboom-operator)<a href="https://agentmods.dev/skills/sandraschi/yahboom-mcp/yahboom-operator"><img src="https://agentmods.dev/badge/skills/sandraschi/yahboom-mcp/yahboom-operator/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/sandraschi/yahboom-mcp/yahboom-operator"><img src="https://agentmods.dev/badge/skills/sandraschi/yahboom-mcp/yahboom-operator.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 | $0.00032 | $0.00675 |
| Opus 5 | $0.00016 | $0.00338 |
| Sonnet 5 | $0.00006 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
yahboom-operator scanned grade A with 0 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 10d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yahboom Raspbot v2 Operator Skill
Use this skill when controlling or troubleshooting a Yahboom Raspbot v2 (or compatible) robot via the Yahboom MCP server. For hardware, ROS 2, frames, and integration depth use yahboom-robots-expert.
🛠️ Tool Set
- yahboom(operation, param1, param2, payload) — Single operation.
operationone of:health_check,forward,backward,turn_left,turn_right,strafe_left,strafe_right,stop,read_imu,read_battery,read_encoders,start_recording,stop_recording,list_trajectories,config_show. Useparam1for speed/duration where applicable. - lidar(operation, source, param1, param2, payload) — LIDAR/map:
operationone ofread,read_raw,read_dreame_map;sourceone ofyahboom,dreame,auto. Yahboom /scan when bridge connected; Dreame D20 Pro scan when DREAME_MAP_URL set. - yahboom_help(category, topic) — Drill-down help. Categories: motion, sensors, connection, api, mcp_tools, startup, troubleshooting.
- yahboom_agentic_workflow(goal) — High-level goal (SEP-1577). Describe what you want the robot to do in natural language; the LLM plans and runs a sequence of health/motion/sensor steps.
📝 Prompts
- yahboom_quick_start(robot_ip) — Setup instructions for connecting the server to the robot.
- yahboom_patrol(duration_seconds) — Get a patrol plan (e.g. square or figure-8).
- yahboom_diagnostics() — Diagnostic checklist for connection and sensors.
- yahboom_patrol_apartment() — Standard action: full circuit of main rooms, avoid obstacles, return to start.
- yahboom_go_to_recharge() — Standard action: drive to charging station and stop (contactless recharger to be equipped later).
🧭 Workflow Rules
- Safety First: Always run
yahboom(operation='health_check')before motion to confirm bridge and battery. - Goal-Oriented: Use
yahboom_agentic_workflowfor multi-step goals (patrol, inspect, return); use singleyahboomcalls for one-off commands. - Power Management: For low battery (< 20%) avoid long motions; suggest charging.
- Knowledge Recall: Recording trajectories:
start_recording, then motion, thenstop_recordingwith a name.
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.
- 10d ago First seen · 36 lines · 32 tokens per session scan A b031195391f7
yahboom-operator is a skill published in the GitHub repository sandraschi/yahboom-mcp (4 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 675 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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…
unifi-access
How to manage UniFi Access door control — locks, credentials, visitors, access policies, and events. Use this skill when the user mentions UniFi Access, door locks, door access, building access, NFC cards, PIN codes, visitor passes, access policies, access schedules, door readers, or any UniFi Access task.
evaluating-cosmos-policy
Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.
fine-tuning-openvla-oft
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying…
network-health-check
Run a UniFi network health check — diagnose device status, connectivity issues, firmware updates, and system health. Use when asked to check network health, find what's down, diagnose connectivity issues, or get a network status summary.
sensing
React to passive sensing events from the device — presence, sound, light, fire hazard. Events arrive as [sensing: ] messages and each gets an emotion marker + optional short line. Does NOT handle motion.activity (→ wellbeing) or emotion.detected / speechemotion.detected (→ user-emotion-detection).