sensecraft-solutions: Skill for Claude Code

.agents/skills/prepare-himax-firmware/SKILL.md

prepare-himax-firmware is a skill for Claude Code from suharvest/sensecraft-solutions. It costs 46 tokens per session (2,128 once invoked), scanned A, original, Apache-2.0.

A guide for preparing Himax WE2 firmware and AI models for SenseCAP Watcher, a device with an ESP32-S3 controller and a Himax chip for vision tasks.

In plain words
What is it for?
Use it to identify the correct serial interfaces, flash firmware with xmodem, configure AI model addresses, and add Himax device support to a solution.
Why use it?
It accounts for the Watcher's two USB interfaces and the reset sequence required to flash the Himax chip without interruption.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is suharvest/sensecraft-solutions's own configuration. It tells Claude Code how to work on sensecraft-solutions itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sensecraft-solutions configures →

Reuse

Borrowing it

Nothing to install: this file belongs to suharvest/sensecraft-solutions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/suharvest/sensecraft-solutions/main/.agents/skills/prepare-himax-firmware/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/suharvest/sensecraft-solutions

Made for: Claude Code.

Wrote 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.

agentmods badge for prepare-himax-firmware

README.md
[![agentmods](https://agentmods.dev/badge/skills/suharvest/sensecraft-solutions/prepare-himax-firmware/github.svg)](https://agentmods.dev/skills/suharvest/sensecraft-solutions/prepare-himax-firmware)
Your own site
<a href="https://agentmods.dev/skills/suharvest/sensecraft-solutions/prepare-himax-firmware"><img src="https://agentmods.dev/badge/skills/suharvest/sensecraft-solutions/prepare-himax-firmware/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prepare-himax-firmware

Your own site · 80×15
<a href="https://agentmods.dev/skills/suharvest/sensecraft-solutions/prepare-himax-firmware"><img src="https://agentmods.dev/badge/skills/suharvest/sensecraft-solutions/prepare-himax-firmware.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,128 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00046 $0.02128
Opus 5 $0.00023 $0.01064
Sonnet 5 $0.00009 $0.00426
Haiku 4.5 $0.00005 $0.00213

Measured 12d ago against content hash 7608b6af5350, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

prepare-himax-firmware 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 12d 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.

.agents/skills/prepare-himax-firmware/SKILL.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prepare Himax WE2 Firmware

Guide for preparing Himax WE2 firmware and AI models for SenseCAP Watcher devices.

Overview

SenseCAP Watcher uses a dual-chip architecture:

  • ESP32-S3: Main controller, WiFi/BLE connectivity
  • Himax WE2: AI accelerator chip for vision tasks

This skill covers flashing firmware and AI models to the Himax WE2 chip.

Key Concepts

USB Interfaces

Watcher exposes two USB serial interfaces:

Interface Pattern (macOS) Pattern (Linux) VID:PID Purpose
Himax WE2 /dev/cu.usbmodem* /dev/ttyACM* 0x1A86:0x55D2 Firmware flashing
ESP32-S3 /dev/cu.wchusbserial* /dev/ttyUSB* 0x1A86:0x55D2 Serial monitor

ESP32 Reset Hold

Critical: During Himax flashing, the ESP32 must be held in reset state. Otherwise, the ESP32 firmware will detect Himax anomalies and reset it, causing flashing to fail.

The deployer automatically handles this by:

  1. Opening ESP32 serial port
  2. Setting DTR=False (holds EN pin low = reset state)
  3. Flashing Himax
  4. Releasing DTR to allow normal boot

Directory Structure

solutions/[solution_id]/
├── solution.yaml
├── guide.md
├── guide_zh.md
├── gallery/
├── assets/
│   ├── watcher_firmware/
│   │   └── firmware.img            # Base firmware
│   └── models/
│       ├── model1.tflite           # AI model 1
│       └── model2.tflite           # AI model 2
└── devices/
    └── watcher_himax.yaml          # Device config

Device Configuration Template

Create devices/watcher_himax.yaml:

version: "1.0"
id: watcher_himax
name: Himax WE2 Face Recognition
name_zh: Himax WE2 人脸识别
type: himax_usb

detection:
  method: usb_serial
  # Watcher Himax WE2 USB identifiers (WCH chip)
  usb_vendor_id: "0x1a86"
  usb_product_id: "0x55d2"
  fallback_ports:
    - "/dev/cu.usbmodem*"
    - "/dev/tty.usbmodem*"
    - "/dev/ttyACM*"

firmware:
  source:
    path: assets/watcher_firmware/firmware.img  # Local path or URL

  flash_config:
    baudrate: 921600
    timeout: 60
    protocol: xmodem                  # xmodem (128B) or xmodem1k (1024B)
    requires_esp32_reset_hold: true   # Critical for SenseCAP Watcher

    # Multi-model configuration
    models:
      - id: face_detection
        name: Face Detection (SCRFD)
        name_zh: 人脸检测模型 (SCRFD)
        path: assets/models/scrfd.tflite
        flash_address: "0x400000"     # Flash memory address
        offset: "0x0"
        required: true
        default: true
        description: Core face detection model
        description_zh: 核心人脸检测模型
        size_hint: "512KB"

      - id: face_embedding
        name: Face Embedding
        name_zh: 人脸特征模型
        path: assets/models/ghostfacenet.tflite
        flash_address: "0x510000"
        offset: "0x0"
        required: true
        default: true
        description: Face recognition embedding model
        description_zh: 人脸识别特征提取模型
        size_hint: "800KB"

user_inputs:
  - id: serial_port
    name: Serial Port
    name_zh: 串口
    type: serial_port
    required: true
    description: Select the USB port for Himax WE2 (usbmodem)
    description_zh: 选择 Himax WE2 的串口(usbmodem 开头)
    auto_detect: true

  - id: model_selection
    name: Models to Flash
    name_zh: 选择要烧录的模型
    type: model_select
    required: false
    description: Select AI models to flash
    description_zh: 选择要烧录的 AI 模型

steps:
  - id: detect
    name: Detect Device
    name_zh: 检测设备
  - id: flash
    name: Flash Firmware & Models
    name_zh: 烧录固件和模型
  - id: verify
    name: Verify
    name_zh: 验证

post_deployment:
  reset_device: false
  wait_for_ready: 5

Read the full file on GitHub · 242 lines

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. 12d ago First seen · 242 lines · 46 tokens per session scan A 7608b6af5350

Subscribe to this mod's changes

prepare-himax-firmware is a skill published in the GitHub repository suharvest/sensecraft-solutions (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 2,128 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

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…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

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…

NVIDIA/skills · 236 tokens

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…

SnailSploit/Claude-Red · 113 tokens

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…

NVIDIA/skills · 94 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens