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 D-Robotics/moss --skill rdk-doc-findergit clone --depth 1 https://github.com/D-Robotics/mossWrote 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/d-robotics/moss/rdk-doc-finder)<a href="https://agentmods.dev/skills/d-robotics/moss/rdk-doc-finder"><img src="https://agentmods.dev/badge/skills/d-robotics/moss/rdk-doc-finder/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/d-robotics/moss/rdk-doc-finder"><img src="https://agentmods.dev/badge/skills/d-robotics/moss/rdk-doc-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 95 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00270 | $0.03054 |
| Opus 5 | $0.00135 | $0.01527 |
| Sonnet 5 | $0.00054 | $0.00611 |
| Haiku 4.5 | $0.00027 | $0.00305 |
Grade A, and why
rdk-doc-finder scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> Sources: the six D-Robotics Docusaurus repos (`rdk_x_doc`, `rdk_s_doc`, `tros_doc`, `model_zoo_doc`, `rdk_studio_doc`, `accessories_doc`, default branch `main`) plus the archived `rdk_doc`. URL rules were checked again How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RDK Official Doc Locator
Point any RDK question at the right official manual, chapter, and verified developer.d-robotics.cc URL. The single most important thing: the docs are split across SIX live sites plus one archive — pick the right site first, then derive the URL, then verify it before handing it over. Never paste a derived URL you have not confirmed 200.
Sources: the six D-Robotics Docusaurus repos (
rdk_x_doc,rdk_s_doc,tros_doc,model_zoo_doc,rdk_studio_doc,accessories_doc, default branchmain) plus the archivedrdk_doc. URL rules were checked against each repo'sdocusaurus.config.js; representative URLs were curl-tested 200/404 (see "Verified anchors"). Docs evolve with releases — when in doubt, re-fetch.
Step 1 — Pick the right site (six-site split)
Each topic belongs to exactly one site. Get this wrong and every URL after it is wrong.
Site (baseUrl) |
Owns | Boards |
|---|---|---|
| rdk_x_doc | X-series main manual: quick start / system config / 40pin / vision / audio / multimedia / toolchain / Linux dev / FAQ / appendix commands | X3 · X3 Module · X5 · X5 Module · Ultra* |
| rdk_s_doc | S-series main manual: all of the above plus MCU dev / hbmem / PCIe / OTA / VDSP (S-only) | S100 · S100P · S600 |
| tros_doc | TROS / ROS2 robotics: install / quick demo / function packages (boxs) / apps / perf tuning | cross-board (X & S) |
| model_zoo_doc | Model Zoo algorithm catalog + usage (precompiled models, infer API, per-board guides) | X3 · X5 · S100 · S600 |
| rdk_studio_doc | RDK Studio desktop client: install/login / flashing / connect device / AI chat / OpenClaw / Skill / CLI / FAQ | Studio app itself |
| accessories_doc | Official accessories: stereo cameras GS130W / GS130WI, IMU module | accessory hardware |
* Ultra has no page in rdk_x_doc — its hardware intro lives only in the archived rdk_doc (see Step 3).
Site-selection cheat-sheet:
| User asks about… | Go to |
|---|---|
| Using a ROS2 node, installing TROS, Nav2, SLAM, stereo/VIO | tros_doc (even on X/S boards) |
| Ready-made YOLO/classification/segmentation model, accuracy figures | model_zoo_doc |
| RDK Studio client UI, OpenClaw, flashing dialog, client errors | rdk_studio_doc |
| S100/S600 MCU / R52 / hbmem / .hbm / PCIe / EtherCAT / OTA / VDSP | rdk_s_doc (X site has no MCU chapter) |
| Other on-board system / peripheral / toolchain topics | X board → rdk_x_doc, S board → rdk_s_doc |
| Stereo camera GS130W/GS130WI, IMU module | accessories_doc |
What ships with it
2 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.
- 9d ago First seen · 125 lines · 270 tokens per session scan A e8f819c78882
rdk-doc-finder is a skill published in the GitHub repository D-Robotics/moss (142 stars, last pushed 13d ago), licensed MIT. It adds 270 tokens to every session and 3,054 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 1 finding (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
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.
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…
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…
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.