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/jetson-knowledgenpx skills add D-Robotics/moss --skill jetson-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/jetson-knowledge)<a href="https://agentmods.dev/skills/d-robotics/moss/jetson-knowledge"><img src="https://agentmods.dev/badge/skills/d-robotics/moss/jetson-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 | $0.00282 | $0.03505 |
| Opus 5 | $0.00141 | $0.01752 |
| Sonnet 5 | $0.00056 | $0.00701 |
| Haiku 4.5 | $0.00028 | $0.00350 |
Grade B, and why
jetson-knowledge scanned grade B 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
All TOPS figures NVIDIA quotes are **INT8 Sparse**; dense INT8 is half. Enable Super Mode after flashing JetPack 6.2 with `sudo nvpmodel -m 2` (Nano) or `sudo nvpmodel -m 0` (NX), then reboot. How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NVIDIA Jetson Knowledge
A clean single-platform reference for NVIDIA Jetson: what each module is, how much AI performance it delivers, which software stack it runs, and how to turn a trained model into a fast on-device TensorRT engine. The single most important thing to get right is the Super Mode TOPS numbers — since JetPack 6.2 (Feb 2025) every Orin Nano / Orin NX TOPS figure changed, and quoting the pre-Super numbers is the most common stale answer.
Sources: NVIDIA official Jetson pages and docs — the Jetson Orin product page, the JetPack 6.2 Super Mode blog, JetPack SDK pages, and the Jetson Product Lifecycle. Every spec below is grounded in those; provenance is noted inline. Specs and "currently shipping" status change — defer to the live NVIDIA selector page when in doubt.
The one thing to get right: Super Mode changed the TOPS
Since JetPack 6.2 (Jetson Linux 36.4.3, Feb 2025), NVIDIA shipped Super Mode — a software-only clock/power boost for Orin Nano and Orin NX modules. It roughly doubles advertised INT8 throughput with no hardware change. When someone asks "how many TOPS is an Orin Nano", answer with the Super number and say it requires JetPack 6.2 + the right nvpmodel profile:
- Orin Nano 8GB / Orin Nano Super: 67 TOPS (was 40 pre-Super)
- Orin Nano 4GB: 34 TOPS
- Orin NX 8GB: 117 TOPS (was 70 pre-Super)
- Orin NX 16GB: 157 TOPS (was 100 pre-Super)
All TOPS figures NVIDIA quotes are INT8 Sparse; dense INT8 is half. Enable Super Mode after flashing JetPack 6.2 with sudo nvpmodel -m 2 (Nano) or sudo nvpmodel -m 0 (NX), then reboot.
Module cheat-sheet (specs → software stack)
Confirm the exact module first (cat /proc/device-tree/model), then read the row. AGX Orin and Xavier NX do not have Super Mode — their numbers are fixed.
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.
- 4d ago First seen · 126 lines · 282 tokens per session scan B 0c10d3c19392
jetson-knowledge is a skill published in the GitHub repository D-Robotics/moss (142 stars, last pushed 8d ago), licensed MIT. It adds 282 tokens to every session and 3,505 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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.
import-prom-rule
Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
unifi-protect
How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, Known Faces, license plates, and the Alarm Manager. Use this skill when the user mentions UniFi cameras, security cameras, NVR, recordings, motion detection, person…
tilelang-env-check
TileLang-Ascend 环境检查与配置验证技能。检查代码仓库完整性、编译安装状态、环境变量配置，并运行简单测试验证环境。发现问题会自动调用相关 skill 进行修复，并按依赖顺序重新执行后续步骤。触发关键词："环境检查"、"检查环境"、"验证环境"、"环境配置"、"环境搭建"、"env check"、"check environment"、"verify environment"、"setup environment"。.
KernelWiki
Use when the user asks about optimizing NVIDIA Blackwell (SM100, B200) or Hopper (SM90, H100) GPU kernels — tcgen05/TMEM/CLC/NVFP4/2-SM cooperative, warp specialization, FlashAttention-4, DeepGEMM, FlashMLA, MoE, grouped GEMM, CuTe-DSL/PTX/Triton on Blackwell, or wants concrete PR references from…