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.
/plugin marketplace add iot-forge/m5stack-skillsnpx agentmods add plugins/iot-forge/m5stack-skills/esp32-chipsgit clone --depth 1 https://github.com/iot-forge/m5stack-skillsGrade A, and why
esp32-chips 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.
What it actually says
{
"name": "esp32-chips",
"displayName": "Espressif SoC capability references",
"version": "0.4.0",
"description": "Chip-level ESP-IDF capability references for the Espressif SoCs behind M5Stack boards: classic ESP32 (Xtensa LX6), ESP32-S3 (Xtensa LX7), ESP32-C6 (RISC-V, WiFi 6 + Thread/Zigbee), and ESP32-P4 (RISC-V, MIPI-DSI/CSI, no radio). Covers peripherals, sleep modes and ULP/LP coprocessors, memory and PSRAM config, USB controllers, radio coexistence, and AI/DSP instruction extensions. Board skills point into these instead of re-deriving the same content per board.",
"author": {
"name": "IoT Forge",
"url": "https://github.com/iot-forge"
},
"keywords": [
"esp32",
"esp32-s3",
"esp32-c6",
"esp32-p4",
"esp-idf",
"espressif",
"risc-v",
"xtensa",
"ulp",
"psram",
"deep-sleep",
"embedded"
],
"license": "MIT",
"homepage": "https://github.com/iot-forge/m5stack-skills",
"repository": "https://github.com/iot-forge/m5stack-skills"
}
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 · 28 lines scan A 3e111acbde36
esp32-chips is a plugin published in the GitHub repository iot-forge/m5stack-skills (2 stars, last pushed 7d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
reterminal-sticky
Claude Code plugins for the Seeed Studio reTerminal Sticky e-ink device.
sticky-device
Hardware, firmware, and publishing context for the Seeed Studio reTerminal Sticky (ESP32-S3 e-ink device).
embedded-agent-skills
Agent Skills for embedded systems development including GPIO configuration, pin validation, and hardware initialization code generation.
gpio-config
GPIO pin assignment, validation, and code generation for Raspberry Pi and ESP32 embedded projects. Supports I2C, SPI, UART, PWM, 1-Wire, CAN, ADC protocols with 28 device profiles and hardware safety warnings.
jlink-mcp
Plugin marketplace listing 1 plugin: jlink-mcp.
membrowse
MemBrowse memory tracking integration for embedded firmware projects. Automatically sets up GitHub workflows for RAM/Flash analysis.