sensecraft-solutions: Skill for Claude Code

.agents/skills/prepare-deb-package/SKILL.md

prepare-deb-package is a skill for Claude Code from suharvest/sensecraft-solutions. It costs 37 tokens per session (2,485 once invoked), scanned A, original, Apache-2.0.

A guide for preparing Debian-format package files for C++ applications deployed to reCamera devices. It includes device settings, startup scripts, package paths, and application deployment files.

In plain words
What is it for?
Use it to configure a reCamera device, create a .deb package, set up its init script, and define how the binary is installed and started.
Why use it?
It accounts for reCamera's embedded Linux environment, which uses opkg instead of apt or dpkg, SysVinit instead of systemd, and RISC-V 64-bit hardware.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument; 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-deb-package/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-deb-package

README.md
[![agentmods](https://agentmods.dev/badge/skills/suharvest/sensecraft-solutions/prepare-deb-package/github.svg)](https://agentmods.dev/skills/suharvest/sensecraft-solutions/prepare-deb-package)
Your own site
<a href="https://agentmods.dev/skills/suharvest/sensecraft-solutions/prepare-deb-package"><img src="https://agentmods.dev/badge/skills/suharvest/sensecraft-solutions/prepare-deb-package/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-deb-package

Your own site · 80×15
<a href="https://agentmods.dev/skills/suharvest/sensecraft-solutions/prepare-deb-package"><img src="https://agentmods.dev/badge/skills/suharvest/sensecraft-solutions/prepare-deb-package.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,485 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 $0.00037 $0.02485
Opus 5 $0.00018 $0.01242
Sonnet 5 $0.00007 $0.00497
Haiku 4.5 $0.00004 $0.00248

Measured 10d ago against content hash 7eff148416f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prepare-deb-package 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 10d 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-deb-package/SKILL.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prepare Debian Packages for reCamera

Guide for creating .deb packages that deploy C++ applications to reCamera devices.

Overview

reCamera devices run a BusyBox-based Linux system that uses:

  • opkg for package management (not apt/dpkg)
  • SysVinit for service management (not systemd)
  • RISCV64 architecture (cv181x chip)

Directory Structure

solutions/[solution_id]/
├── solution.yaml
├── guide.md
├── guide_zh.md
├── gallery/
├── packages/                      # Deb packages and models
│   ├── [app]-detector_x.x.x_riscv64.deb
│   └── [model].cvimodel
└── devices/
    └── recamera_[variant].yaml    # Device config

Device Configuration Template

Create devices/recamera_[variant].yaml:

version: "1.0"
id: recamera_yolo11
name: reCamera YOLO11 Detector
name_zh: reCamera YOLO11 检测器
type: recamera_cpp

detection:
  method: network_scan
  manual_entry: true
  requirements: []

# SSH connection config
ssh:
  port: 22
  default_user: recamera
  default_host: 192.168.42.1
  connection_timeout: 30
  command_timeout: 300

# C++ application deployment config
binary:
  # .deb package (includes init script)
  deb_package:
    path: packages/yolo11-detector_0.1.1_riscv64.deb
    name: yolo11-detector
    includes_init_script: true    # deb contains /etc/init.d/S*

  # Model files
  models:
    - path: packages/model.cvimodel
      target_path: /userdata/local/models
      filename: model.cvimodel

  # Service configuration
  service_name: yolo11-detector
  service_priority: 92            # S92yolo11-detector

  # MQTT external access (optional)
  mqtt_config:
    enable: true
    port: 1883
    allow_anonymous: true

  # Conflict service handling
  conflict_services:
    stop:                         # Stop before deployment
      - S03node-red
      - S91sscma-node
      - S93sscma-supervisor
    disable:                      # Disable autostart (S* -> K*)
      - node-red
      - sscma-node
      - sscma-supervisor

  auto_start: true

> **Cloud materials**: `deb_package.path` and `models[].path` accept URLs (e.g., `https://cdn.example.com/package.deb`). Files are automatically downloaded and cached before deployment.

# User inputs
user_inputs:
  - id: host
    name: Device IP Address
    name_zh: 设备 IP 地址
    type: text
    default: "192.168.42.1"
    required: true
    validation:
      pattern: "^\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}$"

  - id: password
    name: SSH Password
    name_zh: SSH 密码
    type: password
    default: "recamera"
    required: true

# Deployment steps (shown to user)
steps:
  - id: connect
    name: SSH Connect
    name_zh: SSH 连接
  - id: precheck
    name: Check Device State
    name_zh: 检查设备状态
  - id: prepare
    name: Stop Conflicting Services
    name_zh: 停止冲突服务
  - id: transfer
    name: Transfer Files
    name_zh: 传输文件
  - id: install
    name: Install Package
    name_zh: 安装软件包
  - id: models
    name: Deploy Model
    name_zh: 部署模型
  - id: mqtt
    name: Configure MQTT
    name_zh: 配置 MQTT
  - id: disable
    name: Disable Conflicts
    name_zh: 禁用冲突服务
  - id: start
    name: Start Service
    name_zh: 启动服务
  - id: verify
    name: Verify
    name_zh: 验证

post_deployment:
  open_browser: false

Read the full file on GitHub · 348 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. 10d ago First seen · 348 lines · 37 tokens per session scan A 7eff148416f1

Subscribe to this mod's changes

prepare-deb-package is a skill published in the GitHub repository suharvest/sensecraft-solutions (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 2,485 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

systematic-debugging

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

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens