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 Seeed-Projects/Seeed-Jetson-DevelopTool --skill soarm-controlgit clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopToolWrote 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/seeed-projects/seeed-jetson-developtool/soarm-control)<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/soarm-control"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/soarm-control/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/seeed-projects/seeed-jetson-developtool/soarm-control"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/soarm-control.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 | $0.00039 | $0.00798 |
| Opus 5.5 | $0.00016 | $0.00319 |
| Sonnet 5.5 | $0.00008 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
soarm-control 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 4d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SO-ARM101 with DevelopTool
Use this skill only after identifying the actual arm as SO-ARM101. reBot/CAN
arms use their own skill and controller. The task context provides the
DevelopTool bridge command prefix; ssh --command ... executes on the selected
Jetson with the application's saved authentication. Do not run a hardware
command on the PC by mistake.
Reuse configured hardware
- Identify serial devices using
ls -l /dev/serial/by-id /dev/ttyACM* /dev/ttyUSB* 2>/dev/nulland inspect the known running controller/configuration. Prefer its existing state API or ROS topic; don't start a second serial owner. - Check only the exact remote skill paths:
~/.agents/skills/soarm-control/SKILL.md,~/.codex/skills/soarm-control/SKILL.md,~/.claude/skills/soarm-control/SKILL.md,~/.openclaw/workspace/skills/soarm-control/SKILL.md. If a hardware-specific skill is installed there, read its actual scripts and configuration before using them. A skill file on the PC does not establish that its script paths or Conda environment exist on the Jetson. - Reuse the configured LeRobot environment, arm ID, port and calibration.
If setup is missing, use the matched
lerobot-env-setupguide. Do not blindly install dependencies into the system Python or replace a working environment.
Read-only task
Use the current controller's observation endpoint. A deployed skill may supply
scripts/soarm_status.py; inspect the actual implementation and CLI first. Do
not assume connecting/disconnecting its motor bus is a read-only operation:
some wrappers change torque state on connect/disconnect. If no read-only state
endpoint exists, report that limitation instead of creating a competing owner.
Publish measured joint positions, gripper and state with the bridge:
publish --source soarm --json '{"shoulder_pan_deg":<actual measurement>}'.
Use the units and normalization of the actual controller; a LeRobot normalized
position is not automatically degrees. Missing values are unknown, not zero.
Update after fresh observations and let the panel show sample times.
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.
- 4d ago First seen · 68 lines · 39 tokens per session scan A 0dc146316e98
soarm-control is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (56 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 798 once invoked, about $0.0002 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 2026-10-24.
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.
holoscan-install-wheel
Install Holoscan SDK 5.x CUDA 13 Python wheels in an isolated environment, choosing the full stack or version-matched components.
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…