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 agentmods add skills/d-robotics/moss/rdk-board-knowledgenpx skills add D-Robotics/moss --skill rdk-board-knowledgegit 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-board-knowledge)<a href="https://agentmods.dev/skills/d-robotics/moss/rdk-board-knowledge"><img src="https://agentmods.dev/badge/skills/d-robotics/moss/rdk-board-knowledge.svg" alt="Measured on agentmods" 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 | $0.00330 | $0.04876 |
| Opus 5 | $0.00165 | $0.02438 |
| Sonnet 5 | $0.00066 | $0.00975 |
| Haiku 4.5 | $0.00033 | $0.00488 |
Grade D, and why
rdk-board-knowledge scanned grade D 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 5d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
1. **Host prep** — connect PC USB ↔ board **Type-C** with a high-quality short shielded cable. Linux: `sudo apt install android-tools-adb android-tools-fastboot dfu-util`. Windows: install `sunrise5_winusb` driver (run ` Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **dangerous** (can destroy the system / needs explicit OK): `dd`, `mkfs`, `rm -rf /`, `fdisk`/`parted`, flash erase, `modules_install`/`depmod`, writes to `/boot` · `/lib/modules` · `/etc/fstab`, bootloader/initramfs c How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RDK Board Baseline & Failure Diagnosis
Before answering any RDK problem, confirm the board from on-board facts, not from the user's words. The board determines every downstream answer — package names, TROS path, toolchain, camera node, default IP. Guessing the board (e.g. assuming X5) is the single most common way these answers go wrong.
Sources: official D-Robotics docs
rdk_doc/rdk_x_doc/rdk_s_doc(08_FAQ + 01_Quick_start/install_os), the OpenExplorer / 天工开物 (TianGong) toolchains, and reproduced community cases. Facts are carried over with provenance; nothing is invented.
The one move that matters most
Run a read-only identity probe first. Never flash, upgrade, or drive GPIO before you know the board:
cat /sys/class/socinfo/board_id # X5 / S-series read this (srpi-config, hobot_mipi_cam use it)
cat /sys/class/socinfo/som_name # X3 docs use som_name; pick one per board
cat /proc/device-tree/model # literal model string; fallback /etc/board_config.json
cat /etc/version # OS/RDK image version (2.1.0+ also has `rdkos_info`)
If the output doesn't map cleanly to X3/X5/Ultra/S100/S100P/S600, ask for more logs — do not assume X5.
Board baseline cheat-sheet
| Board | BPU arch | OS / TROS | Default IP (wired) | Power | Flash method |
|---|---|---|---|---|---|
| RDK X3 | Bernoulli2 (bernoulli2) |
Ubuntu 20.04/22.04, Humble (/opt/tros/humble) |
2.1.0+ 192.168.127.10 (≤2.0.0 192.168.1.10) |
Type-C 5V/3A+ | SD card (balenaEtcher / official flasher) |
| RDK X5 | Bayes-e (bayes-e) |
Ubuntu 22.04, Humble | wired 192.168.127.10, USB-net 192.168.128.10 |
5V/5A | SD card |
| RDK Ultra | Bayes (bayes) |
Ubuntu 20.04, Foxy/Humble | DHCP | 12V/5A DC | SD card |
| RDK S100 | Nash-e (nash-e) |
Ubuntu 22.04, Humble (tros-humble) |
eth1 fixed 192.168.127.10, eth0 DHCP |
12–20V (typ. 12V/5.5A ~70W) | xburn (media emmc) |
| RDK S100P | Nash-m (nash-m) |
Ubuntu 22.04, Humble | eth1 fixed 192.168.127.10 |
12–20V | xburn (media emmc) |
| RDK S600 | Nash (nash-p) |
Ubuntu 24.04, Jazzy (/opt/tros/jazzy, tros-jazzy) |
eth1 fixed 192.168.127.10 |
12–28V (adapter 24V/8A) | xburn (media ufs) |
What ships with it
6 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.
- 5d ago First seen · 148 lines · 330 tokens per session scan D 2b93d605913b
rdk-board-knowledge is a skill published in the GitHub repository D-Robotics/moss (142 stars, last pushed 9d ago), licensed MIT. It adds 330 tokens to every session and 4,876 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
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…