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 cfrs2005/mcp-gs-robot --skill gs-robotgit clone --depth 1 https://github.com/cfrs2005/mcp-gs-robotWrote 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/cfrs2005/mcp-gs-robot/gs-robot)<a href="https://agentmods.dev/skills/cfrs2005/mcp-gs-robot/gs-robot"><img src="https://agentmods.dev/badge/skills/cfrs2005/mcp-gs-robot/gs-robot/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/cfrs2005/mcp-gs-robot/gs-robot"><img src="https://agentmods.dev/badge/skills/cfrs2005/mcp-gs-robot/gs-robot.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 | $0.00086 | $0.03057 |
| Opus 5.5 | $0.00034 | $0.01223 |
| Sonnet 5.5 | $0.00017 | $0.00611 |
| Haiku 4.5 | $0.00009 | $0.00306 |
Grade A, and why
gs-robot 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 today.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gs-robot — Agent Skill for operating Gausium robots
This skill teaches an AI assistant to operate Gausium cleaning robots through the mcp-gs-robot MCP tools (OpenAPI V3). Tool names match the registry in ARCHITECTURE_V3.md §3; inputs are always snake_case and the handlers map them to the documented camelCase.
When to use
- The user mentions Gausium / 高仙 robots, or a robot serial number (robot_sn) shaped like
GS…-…orTEST00-0000-000-X014. - The user asks to: check status, look at maps/resources, create task definitions, start/pause/resume/stop tasks, plan schedules, send a robot home, read task reports.
- The user mentions the
mcp-gs-robotserver, the Saodi (扫地僧) agent, or this repository's MCP/HTTP entry points.
Not for: applying for an open-platform account or obtaining OAuth credentials (point the user to https://developer.gs-robot.com/v3docs/en_US/OpenAPI%20V3/Quick%20Start).
Prerequisites
MCP configuration
The host (Claude Code / Codex / WorkBuddy) must mount the mcp-gs-robot MCP server (stdio entry gs_openapi.main / mcp-gs-robot). Once started, tools are registered by name and can be called directly. The REST / agent SSE entry is gs-robot-server (/api/v1/...); this skill uses MCP tool calls by default.
Environment variables (ARCHITECTURE_V3.md §2)
| Variable | Required | Description |
|---|---|---|
GS_CLIENT_ID / GS_CLIENT_SECRET / GS_OPEN_ACCESS_KEY |
yes | Open-platform credentials (the AccessKeySecret goes into GS_OPEN_ACCESS_KEY) |
GS_BASE_URL |
no | Default https://openapi.gs-robot.com/ |
GS_HTTP_TIMEOUT |
no | Seconds, default 30 |
GS_SERVER_API_KEY |
no | When set, the HTTP server checks X-API-Key |
SAODI_AUTO_APPROVE |
no | 1 skips the second confirmation for dangerous tools (confirmation is on by default) |
Tokens are refreshed automatically by gs_openapi.auth.token_manager; callers never refresh by hand.
Standard workflow
Core order: status → capabilities → resources → task definition → start → poll the command status. Each step lists the tool and its key parameters; dangerous tools (dangerous ✔) follow the safety rules in the next section.
What ships with it
7 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.
- today Changed · +7 lines 4f4e13bdcb94
- yesterday First seen · 117 lines · 86 tokens per session scan A d186e07db0ca
gs-robot is a skill published in the GitHub repository cfrs2005/mcp-gs-robot (4 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 3,057 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.