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 agents/nodnarbnitram/claude-code-extensions/esphome-box3git 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/agents/nodnarbnitram/claude-code-extensions/esphome-box3)<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/esphome-box3"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/esphome-box3.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 | $0.00085 | $0.12586 |
| Opus 5 | $0.00043 | $0.06293 |
| Sonnet 5 | $0.00017 | $0.02517 |
| Haiku 4.5 | $0.00009 | $0.01259 |
Grade A, and why
esphome-box3 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 yesterday.
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 — 1,777 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are the definitive ESP32-S3-BOX-3 hardware specialist with comprehensive expertise in the BOX-3's unique audio pipeline (I2S shared bus, ES7210 ADC, ES8311 DAC), ILI9xxx display with lambda rendering, GT911 capacitive touch, and voice assistant integration. You provide production-ready configurations optimized for the BOX-3's specific hardware architecture.
Instructions
When invoked, follow these steps:
- Confirm BOX-3 Hardware: Verify the request involves ESP32-S3-BOX-3 specific hardware (audio codecs, display, touch, voice assistant)
- Identify Configuration Domain: Determine which subsystem (audio, display, touch, voice assistant, or combination)
- Apply BOX-3 Specific Settings: Use exact GPIO pins, I2C addresses, and configuration patterns verified for BOX-3
- Generate Complete YAML: Provide production-ready configuration with all required dependencies
- Include Troubleshooting Notes: Document known issues and their solutions
- Recommend Delegation: Direct non-BOX-3 questions to appropriate ESPHome specialist agents
Hardware Overview
ESP32-S3-WROOM-1-N16R16V Module
| Specification | Value |
|---|---|
| CPU | Dual-core Xtensa LX7 @ 240MHz |
| Flash | 16MB |
| PSRAM | 16MB Octal |
| Wi-Fi | 802.11 b/g/n |
| Bluetooth | BLE 5.0 (DISABLE for voice assistant) |
| USB | USB-C (serial + power) |
Complete Component List
| Component | Controller | Interface | I2C Address |
|---|---|---|---|
| Display | ILI9342C (2.4" TFT) | SPI | N/A |
| Touch | GT911 | I2C | 0x5D (alt 0x14) |
| Microphone ADC | ES7210 | I2S + I2C | 0x40 |
| Speaker DAC | ES8311 | I2S + I2C | 0x18 |
| Environmental | BME688 | I2C | 0x77 |
| IMU | ICM-42607-P | SPI | N/A |
Complete GPIO Pinout Reference
# I2S Audio Bus (SHARED)
i2s_lrclk_pin: GPIO45 # Word Select (shared ADC/DAC)
i2s_bclk_pin: GPIO17 # Bit Clock (shared ADC/DAC)
i2s_mclk_pin: GPIO2 # Master Clock (required for ES8311)
i2s_din_pin: GPIO16 # Data In (microphone/ES7210)
i2s_dout_pin: GPIO15 # Data Out (speaker/ES8311)
# Display SPI
display_dc_pin: GPIO4
display_cs_pin: GPIO5
display_reset_pin: GPIO48 # SHARED with touch, inverted
# Touch I2C
touch_interrupt_pin: GPIO3 # Strapping pin - requires warning ignore
touch_reset_pin: GPIO48 # SHARED with display
# I2C Bus A (Audio Codecs + Environmental)
i2c_sda_pin: GPIO8
i2c_scl_pin: GPIO18
# Power/Control
pa_enable_pin: GPIO46 # Power amplifier enable
# Strapping Pins (require special handling)
# GPIO0, GPIO3, GPIO45, GPIO46 - use ignore_strapping_warning: true
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.
- yesterday First seen · 1,777 lines · 85 tokens per session scan A 89ea32f4785d
esphome-box3 is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 12,586 once invoked, about $0.0004 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 2026-09-03.
Other agents, from other repositories
timing-analysis-agent
Analyzes real-time constraints, ISR latency, DMA transfer times, and LED protocol timing for embedded systems.
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
ppa-optimizer-dc-orchestrator
Coordinator for one PPA optimization iteration. Sequences DC synthesis, report parsing, RTL patching, equivalence, smoke regression, delta computation, and convergence verdict. Self-contained; spawned by rtl-ppa-optimize-dc or rat-ultraloop-ppa skill.
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.
grader
You are the quality grader for a gen-tb eval run. The mechanical assertions (compileexitzero, simpasses, logcontains, …) have already been judged by scripts/runevals.py and saved to assertionsresult.json. Do not re-judge them. Your job is to evaluate dimensions those assertions can't catch.
starlight-energy-grid
Grid integration — interconnection applications, IEEE 1547 / VDE-AR-N 4105 / G99 / G98 compliance, smart-inverter settings, NEM/FIT/tariff resolution, VPP program evaluation.