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-ecosystemnpx skills add D-Robotics/moss --skill rdk-ecosystemgit 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-ecosystem)<a href="https://agentmods.dev/skills/d-robotics/moss/rdk-ecosystem"><img src="https://agentmods.dev/badge/skills/d-robotics/moss/rdk-ecosystem.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 5.1 | $0.00319 | $0.04623 |
| Opus 5 | $0.00160 | $0.02312 |
| Sonnet 5 | $0.00064 | $0.00925 |
| Haiku 4.5 | $0.00032 | $0.00462 |
Grade A, and why
rdk-ecosystem 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 6d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RDK Ecosystem & Board Selection
Help a user pick the right RDK board, judge whether a model will actually run on it, position RDK honestly against Jetson / Raspberry Pi / RK3588, and find the official entry points. The single most common failure is over-promising LLM — telling someone an X5 can "run DeepSeek" smoothly. Calibrate expectations against the official benchmark numbers below, then route the build to the deployment skills.
Sources: D-Robotics official docs (rdk_x_doc, rdk_s_doc, tros_doc, model_zoo_doc) and competitor official docs (NVIDIA, Raspberry Pi). Every benchmark and spec in this skill is grounded in those sources; provenance is noted inline.
The rule that matters most
"Can run" ≠ "usable." A board that technically loads a 7B model at 6.7 TPS is not a usable chat experience. Always quote the official TPS / fps, then say plainly whether it is smooth, tolerable, or a toy. Never let a user buy an X5 expecting a 7B local chatbot — that is the most damaging wrong answer in this whole skill.
Board selection cheat-sheet
Official specs (rdk_x_doc / rdk_s_doc hardware-introduction pages). All artifacts are cross-architecture incompatible — .bin (X-series) and .hbm (S-series) never interchange.
| Board | Gen | Compute | CPU / MCU | RAM | Artifact | Best for |
|---|---|---|---|---|---|---|
| X3 | 1 | Bernoulli2 BPU (~5 TOPS INT8) | 4× A53 | 1/2GB | .bin |
Teaching, light detection, GPIO/ROS2 intro |
| X5 | 2 | Bayes-e BPU (~10 TOPS INT8) | 8× A55 | 4/8GB | .bin |
Robot-vision mainstay; small LLM ≤2B + 1-2B VLM |
| Ultra | 2+ | Bayes BPU (~96 TOPS) | 8× A55 | — | .bin |
High-compute industrial; individuals prefer X5/S100 |
| S100 | 3 | 1× Nash-e BPU, 80 TOPS | 6× A78AE / 4× R52+ | 12GB | .hbm |
Embodied AI; 1.5-3B LLM/VLM + MCU real-time control |
| S100P | 3 | 1× Nash-m BPU, 128 TOPS | 6× A78AE / 4× R52+ | 24GB | .hbm |
S100 + larger models, multi-GMSL camera |
| S600 | 3+ | 4× Nash BPU, 560 TOPS | 18× A78AE / 6× R52+ | 32/64GB | .hbm |
Top compute; smooth 7-8B LLM, dual-arm, 2× 10GbE |
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.
- 6d ago First seen · 146 lines · 319 tokens per session scan A 057b0b99f0cf
rdk-ecosystem is a skill published in the GitHub repository D-Robotics/moss (142 stars, last pushed 10d ago), licensed MIT. It adds 319 tokens to every session and 4,623 once invoked, about $0.0016 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 2026-08-30.
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…