host-software-dev

A reference for software and tools that run on the x86 development computer used with RDK boards. It covers RDK Studio, board flashing, Docker-based model conversion, and development of the Studio application.

In plain words
What is it for?
Use it to install or operate RDK Studio, flash boards, run the Docker BPU toolchain, connect to a board, or work on the Electron, React, Vite, Node, and TypeScript Studio codebase.
Why use it?
Some tasks belong on the computer and others on the board. Confusing the two can lead to running model conversion or flashing commands in the wrong place.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/d-robotics/moss/host-software-dev
Any agent
npx skills add D-Robotics/moss --skill host-software-dev
Clone the repo
git clone --depth 1 https://github.com/D-Robotics/moss

Made for: Claude Code, Codex.

Per session 276 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,296 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00276 $0.03296
Opus 5 $0.00138 $0.01648
Sonnet 5 $0.00055 $0.00659
Haiku 4.5 $0.00028 $0.00330

Measured 2d ago against content hash 1d067fc0f732, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

host-software-dev 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 2d 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.

3. **Add the user to the docker group** so root is not required: `sudo groupadd docker && sudo gpasswd -a ${USER} docker && sudo service docker restart`.
packages/moss-agent/assets/rdk-knowledge/skills/host-software-dev/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RDK Host Software & Tooling

Everything a user does on the x86 PC to develop for RDK: drive the RDK Studio desktop client, flash a board, set up the Docker BPU toolchain, or — if you are building Studio itself — fix its Electron/React/Vite/Node engineering. The single most important reflex: decide whether the task runs on the PC (this skill) or on the board (rdk-device) before answering.

Sources: official rdk_studio_doc (product intro, quick-start, CLI), rdk_doc install_os & toolchain chapters, rdk_s_doc Xburn flashing, plus framework docs (Electron, Vite, TypeScript, Node). Every non-trivial claim is verified against these; nothing is invented.

The one distinction that matters most

Host vs. board. The PC runs RDK Studio, the flasher, and the model-conversion Docker. The board runs the OS, the runtime (hobot_dnn/hbm_runtime), and the camera. Two hard rules that follow:

  • ✅ Model conversion (hb_mapper / hb_compile) runs only on an x86 Linux host inside Docker — never on the board.
  • ❌ RDK Studio's desktop client ships only for Windows 10/11 (64-bit) and macOS Apple-Silicon — there is no Intel-Mac, 32-bit Windows, or Linux desktop installer. For Linux/CI, use the rdkstudio / dmoss-agent CLI instead.

Host-task cheat-sheet

User wants to… Host tool Key fact
Install RDK Studio .exe (Win 10/11 64-bit) or .dmg (macOS Apple Silicon) No Intel-Mac / Linux / 32-bit build; download from developer.d-robotics.cc/rdkstudio
Flash X3 / X5 (SD) RDK Studio flasher or Rufus Writes .img to a ≥16 GB Micro SD; X5 eMMC variants have an eMMC flow
Flash S100 / S600 (USB) Xburn (Win/macOS/Linux) USB DFU+Fastboot (bricked/blank) or Fastboot (re-flash); Win needs the sunrise5_winusb driver
Connect a board with no LAN IP RDK Studio Type-C 直连 Device side 192.168.128.10; full-function Type-C cable; default root/root
Convert .pt/.onnx.bin (X3/X5/Ultra) hb_mapper in OpenExplorer Docker Host: Ubuntu 20.04, ≥16 GB RAM, Docker 19.03+; GPU optional. X5 image ..._x5_*, X3 image ..._x3j5_*
Convert → .hbm (S100/S100P/S600) hb_compile in OpenExplorer Docker Host Docker ai_toolchain_ubuntu_22_s100_s600_*
Script Studio without the GUI rdkstudio CLI / dmoss-agent (@dmoss/agent) Enable rdkstudio from 配置中心 → 应用与更新; dmoss-agent is the standalone NPM pkg for CI/Docker
Build / debug RDK Studio itself Electron + React + Vite + Node/TS See Workflow 4 and references/desktop-app-engineering.md

Read the full file on GitHub · 107 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 107 lines · 276 tokens per session scan B 1d067fc0f732

Subscribe to this mod's changes

host-software-dev is a skill published in the GitHub repository D-Robotics/moss (143 stars, last pushed 6d ago), licensed MIT. It adds 276 tokens to every session and 3,296 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens