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/nodnarbnitram/claude-code-extensions/esphome-box3-buildernpx skills add nodnarbnitram/claude-code-extensions --skill esphome-box3-buildergit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWrote 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/nodnarbnitram/claude-code-extensions/esphome-box3-builder)<a href="https://agentmods.dev/skills/nodnarbnitram/claude-code-extensions/esphome-box3-builder"><img src="https://agentmods.dev/badge/skills/nodnarbnitram/claude-code-extensions/esphome-box3-builder.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 | $0.00148 | $0.03948 |
| Opus 5 | $0.00074 | $0.01974 |
| Sonnet 5 | $0.00030 | $0.00790 |
| Haiku 4.5 | $0.00015 | $0.00395 |
Grade A, and why
esphome-box3-builder 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 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.
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 — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESP32-S3-BOX-3 Builder Skill
Specialist skill for ESP32-S3-BOX-3 hardware providing complete configuration templates, display lambda cookbook, touch interaction patterns, and voice assistant integration for complex audio/display/touch projects.
Purpose
This skill accelerates ESP32-S3-BOX-3 development by providing:
- Complete hardware initialization templates
- Display lambda rendering cookbook (text, shapes, icons, multi-page UI)
- Audio pipeline recipes (I²S, ES7210 ADC, ES8311 DAC)
- Touch interaction patterns (buttons, swipes, gestures)
- Voice assistant integration (wake word, ducking, Home Assistant Assist)
- Material Design UI components
- Hardware-specific troubleshooting and workarounds
Use this skill for ESP32-S3-BOX-3 specific projects. For general ESPHome configuration, use the esphome-config-helper skill instead.
When to Use This Skill
Use this skill when:
- Configuring ESP32-S3-BOX-3 hardware from scratch
- Implementing display lambda rendering (ILI9xxx)
- Setting up I²S audio pipeline (ES7210, ES8311)
- Configuring GT911 touch interaction
- Building voice assistant with wake word detection
- Creating multi-page touchscreen UI
- Troubleshooting BOX-3 specific issues
Delegate to specialized ESPHome agents for:
- Deep technical explanations (esphome-box3 agent)
- General ESPHome concepts (esphome-core agent)
- Network configuration (esphome-networking agent)
Hardware Overview
The ESP32-S3-BOX-3 is a complete development kit with:
- Module: ESP32-S3-WROOM-1 (16MB Flash, 16MB Octal PSRAM)
- Display: ILI9342C (320x240, SPI, PSRAM required for 16-bit color)
- Touch: GT911 capacitive (I²C, multi-touch)
- Microphone: ES7210 4-channel ADC (I²S, 16kHz)
- Speaker: ES8311 mono DAC (I²S, 48kHz, requires MCLK)
- Sensors: BME688 environmental, ICM-42607-P IMU
Critical Requirements:
- PSRAM must be explicitly configured (2025.2+ breaking change)
- ESP-IDF framework recommended (better audio/display support)
- Shared I²S bus for microphone and speaker
- Reset pin GPIO48 shared between display and touch
What ships with it
8 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 · 497 lines · 148 tokens per session scan A b3b16515949c
esphome-box3-builder is a skill published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 148 tokens to every session and 3,948 once invoked, about $0.0007 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
vibecomfy
Drive the VibeComfy package to discover ComfyUI workflows, load ready Python templates, edit and compose them in a VibeWorkflow IR, validate, and execute either embedded locally, against an existing ComfyUI server, or on RunPod. Use whenever the user wants to generate images/video/audio/edits from ComfyUI workflows…
rdk-capture-photo
在已连接的 RDK 开发板上用板载 MIPI sensor 拍照出 JPEG。走 getispdata 专用工具，不碰 /dev/video、不停 cam-service、等 AEC/AWB 收敛取帧。用户说"用开发板拍几张照片/拍照"时使用。调画质（白平衡/曝光/降噪）不在此，用 rdk-isp-tuning。.
xiaoai-tts
Control Xiaoai speaker via OpenXiaoAI Voice API for high-quality TTS playback. Use when the user wants to play voice notifications, announcements, or TTS through the Xiaoai speaker using the OpenXiaoAI HTTP API. Supports Doubao (ByteDance) TTS with emotions, voice types, and speed control. Triggers on queries like…
kernelcad-from-reference
Reproduce a real-world artifact from one or more reference photographs using kernelCAD primitives. Orchestrator skill — names sub-skills and their order. Load this first; it points at the right sub-skill for each stage.
meshy-3d-printing
3D print models generated with Meshy AI, plus Creative Lab consumer products. Handles slicer detection, white model printing, multi-color printing via API, the Creative Lab pipeline (figure / lamp / keychain / fridge-magnet), and print-optimized download workflows. Use when the user mentions 3D printing, slicing…
borkdude
Guidance for selecting the right ClojureScript runtime across scripting, browser, Node, and embedded use.