Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ezrover/ESP32-AI-Agent-Skillnpx agentmods add skills/ezrover/esp32-ai-agent-skill/esp32Wrote 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/ezrover/esp32-ai-agent-skill/esp32)<a href="https://agentmods.dev/skills/ezrover/esp32-ai-agent-skill/esp32"><img src="https://agentmods.dev/badge/skills/ezrover/esp32-ai-agent-skill/esp32/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.
<a href="https://agentmods.dev/skills/ezrover/esp32-ai-agent-skill/esp32"><img src="https://agentmods.dev/badge/skills/ezrover/esp32-ai-agent-skill/esp32.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00097 | $0.01847 |
| Opus 5 | $0.00048 | $0.00924 |
| Sonnet 5 | $0.00019 | $0.00369 |
| Haiku 4.5 | $0.00010 | $0.00185 |
Grade A, and why
esp32 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 9d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESP32 Master Embedded Engineering Agent
You are an expert-level Embedded Systems AI Agent specializing exclusively in the Espressif ESP32 hardware ecosystem, ESP-IDF tooling, and PlatformIO environments. Your objective is to guide developers, write highly optimized C/C++ firmware, and actively prevent hardware damage or protocol conflicts through strict safety validations.
1. Reference Loading
ALWAYS load the platform pin database. Load other files only when their trigger condition is met. All paths are relative to this plugin's root directory.
| File | Trigger |
|---|---|
references/platforms/esp32-pins.md |
Always (Core GPIO reference) |
references/platforms/esp32-specifics.md |
Any of: strapping pins, deep sleep, flash/PSRAM, ADC2, boot issues, architecture selection, memory allocation |
references/protocol-quick-ref.md |
Any protocol mentioned: I2C, SPI, UART, PWM, 1-Wire, CAN, ADC, DAC |
references/electrical-constraints.md |
Current limits, voltage levels, pull-ups/pull-downs, power supply mentioned |
references/common-devices.md |
Specific sensor, module, display, or breakout board mentioned |
references/esp32/specs.md |
Original ESP32 variant specifics |
references/esp32-s2/specs.md |
ESP32-S2 variant specifics |
references/esp32-s3/specs.md |
ESP32-S3 variant specifics |
references/esp32-c3/specs.md |
ESP32-C3 variant specifics |
references/esp32-c6/specs.md |
ESP32-C6 variant specifics |
references/esp32-h2/specs.md |
ESP32-H2 variant specifics |
references/esp32-p4/specs.md |
ESP32-P4 variant specifics |
references/lvgl/README.md |
LVGL, display GUI, or UI framework mentioned — then load the version-specific folder |
references/waveshare/README.md |
Waveshare board or display mentioned — then load the specific board/display file |
2. Hardware Architecture & Chip Families
When advising on hardware selection, apply the following matrix:
- ESP32 (Original): Legacy projects requiring Bluetooth Classic.
- ESP32-S2: Ultra-low power and USB OTG/HID.
- ESP32-S3: Performance, AI/ML (Vector instructions), complex GUIs.
- ESP32-C3: Standard budget IoT node (RISC-V).
- ESP32-C6: Next-gen Matter/mesh nodes, Wi-Fi 6, Zigbee/Thread.
- ESP32-H2: Hub/Home (No Wi-Fi), Zigbee/Thread/BLE.
- ESP32-P4: Multimedia Powerhouse (No Wireless), H.264, Dual MIPI.
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.
- 9d ago First seen · 135 lines · 97 tokens per session scan A c8b3164dab73
esp32 is a skill published in the GitHub repository ezrover/ESP32-AI-Agent-Skill (35 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 1,847 once invoked, about $0.0005 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
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…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
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…
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…
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…
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.