Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/D-Robotics/mossnpx agentmods add skills/d-robotics/moss/rdk-model-zooWrote 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-model-zoo)<a href="https://agentmods.dev/skills/d-robotics/moss/rdk-model-zoo"><img src="https://agentmods.dev/badge/skills/d-robotics/moss/rdk-model-zoo.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00296 | $0.03159 |
| Opus 5 | $0.00148 | $0.01580 |
| Sonnet 5 | $0.00059 | $0.00632 |
| Haiku 4.5 | $0.00030 | $0.00316 |
Grade A, and why
rdk-model-zoo 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 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.
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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RDK Model Zoo — Ready-Made BPU Models
The Model Zoo is the official collection of out-of-the-box, pre-compiled BPU models plus full-link conversion tutorials. The single most important fact: the branch you clone IS your board. Cloning the wrong branch is the #1 failure — the model artifact or the runtime API will not match your hardware.
Sources: official D-Robotics repos verified for this skill — rdk_model_zoo (
rdk_x5/rdk_x3/rdk_sbranches), rdk_model_zoo_s (s100archive), and model_zoo_doc appendix benchmarks. Facts carry provenance; nothing is invented.
The one rule that matters most
Branch = board. Confirm the board first (cat /sys/class/socinfo/board_id, or rdkos_info for the full OS/board summary), then clone exactly that branch. A .bin (Bayes / Bernoulli2) and a .hbm (Nash) are never interchangeable, and the Python runtime import differs by branch. Do not recite directory or model names from memory — ls samples/ on the actual checked-out branch is the source of truth.
Branch → board cheat-sheet (the foundation)
| Board | Repo | Branch | Sample dir | Artifact | Python runtime |
|---|---|---|---|---|---|
| RDK X5 | rdk_model_zoo |
rdk_x5 |
samples/vision/<model>/ |
.bin |
hbm_runtime |
| RDK X5 (legacy) | rdk_model_zoo |
rdk_x5_legacy |
(old demos) | .bin |
hobot_dnn / pyeasy_dnn |
| RDK X3 | rdk_model_zoo |
rdk_x3 |
demos/<task>/ (note: demos/, not samples/) |
.bin |
pyeasy_dnn / hobot_dnn |
| RDK S100 / S100P / S600 | rdk_model_zoo |
rdk_s |
samples/vision/<model>/ |
.hbm |
hbm_runtime |
| RDK S100 / S100P (archive) | rdk_model_zoo_s |
s100 |
samples/Vision/<Model>/ |
.hbm |
hbm_runtime |
Verified against the live rdk_x5 and rdk_s branch READMEs. The rdk_s branch is now the single current delivery branch for S100, S100P, AND S600 (its README: "Current branch. Primary delivery branch for RDK S100, S100P, and S600"). rdk_model_zoo_s/s100 is the historical archive — still complete and runnable, but rdk_s is the one to use for new work. A deterministic branch lookup is in scripts/branch_selector.py.
What ships with it
4 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 · 117 lines · 296 tokens per session scan A 85d8133e3750
rdk-model-zoo is a skill published in the GitHub repository D-Robotics/moss (142 stars, last pushed 13d ago), licensed MIT. It adds 296 tokens to every session and 3,159 once invoked, about $0.0015 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
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
amc-run-rtsp-calibration
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.
amc-run-video-calibration
Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.