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 skills add johnkozaris/jko-claude-plugins --skill esp32-expertgit clone --depth 1 https://github.com/johnkozaris/jko-claude-pluginsWrote 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/johnkozaris/jko-claude-plugins/esp32-expert)<a href="https://agentmods.dev/skills/johnkozaris/jko-claude-plugins/esp32-expert"><img src="https://agentmods.dev/badge/skills/johnkozaris/jko-claude-plugins/esp32-expert/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/johnkozaris/jko-claude-plugins/esp32-expert"><img src="https://agentmods.dev/badge/skills/johnkozaris/jko-claude-plugins/esp32-expert.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00137 | $0.00957 |
| Opus 5 | $0.00068 | $0.00478 |
| Sonnet 5 | $0.00027 | $0.00191 |
| Haiku 4.5 | $0.00014 | $0.00096 |
Grade A, and why
esp32-expert 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESP32 Expert
Identify the chip/board, SDK/framework and version, build frontend, and selected
configuration independently from platformio.ini, CMakeLists.txt, sdkconfig,
and build output. PlatformIO may build Arduino-ESP32 or ESP-IDF; inspect the
selected environment's platform, board, framework, and overrides.
Chip families differ in cores, radio support, memory, peripherals, DMA, and
instruction set. If the target or attached hardware is unfamiliar, read its
current datasheet and support matrix instead of inferring capabilities from the
family name.
Opinions worth carrying
- Reason from field behavior, not compilation. Ask what happens after weeks of uptime, during OTA, under radio reconnect storms, at low voltage, or when a peripheral holds a bus. Report when hardware validation was not possible.
- Treat context as part of the type. Task, ISR, timer callback, event-loop, and normal thread contexts have different legal operations. A helper safe in one may deadlock, allocate illegally, or touch flash unsafely in another.
- Bound every resource. Task stacks, queues, retries, waits, allocations, payloads, and reconnect loops need explicit limits. Unbounded behavior becomes a watchdog reset, heap exhaustion, flash wear, or latency collapse in the field.
- Prefer ownership and message passing over shared mutable state. Choose FreeRTOS primitives for the access pattern, keep ISR work minimal, and account for SMP when the chip has multiple cores. Do not fix races by disabling interrupts on only one core.
- Design memory placement deliberately. Internal RAM, IRAM, DRAM, PSRAM, DMA-capable memory, RTC memory, and flash are not interchangeable. Verify the requirements of the peripheral and API before moving buffers.
- Make recovery explicit. Separate transient faults from invalid configuration and hardware failure. Retries require backoff, a ceiling, and an observable terminal state. A watchdog is a last-resort recovery mechanism, not normal control flow.
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.
- 9d ago First seen · 77 lines · 137 tokens per session scan A 09fd40cd00db
esp32-expert is a skill published in the GitHub repository johnkozaris/jko-claude-plugins (11 stars, last pushed 13d ago), licensed MIT. It adds 137 tokens to every session and 957 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
esp32-expert
This skill should be used when the user is writing, reviewing, debugging, or architecting C++ firmware for ESP32 and variants (ESP32-S2, S3, C3, C6, H2, P4) using ESP-IDF or PlatformIO. Provides expert critique covering FreeRTOS task design, memory management (IRAM/DRAM/PSRAM), peripheral drivers (I2C/SPI/UART/GPIO)…
analyze-github-issue
A workflow for deeply assessing one GitHub issue, including whether it is a real bug or a reasonable feature request.
dotnet-backend-expert
This skill should be used when the user is writing, reviewing, debugging, or architecting pure .NET backend code for Kestrel-hosted services. It provides expert critique for REST endpoints, SignalR hubs, TypeScript/React client integration shape, pragmatic Rust interop, application services, AppHost-aware project…
python-backend-expert
This skill should be used when the user is writing, reviewing, debugging, or architecting Python backend code using Litestar or FastAPI with SQLAlchemy or Advanced Alchemy. Provides expert critique covering SOLID principles, hexagonal architecture, repository/service patterns, dependency injection, async correctness…
rust-expert
This skill should be used when the user is writing, reviewing, debugging, or architecting Rust code. Detects edition and toolchain from the project. Provides expert critique covering ownership, error handling, unsafe review, async correctness, trait design, type system patterns, performance, SOLID principles, and…
swiftui-expert
This skill should be used when the user is building, reviewing, or debugging SwiftUI views and apps. Detects iOS and Swift version from the project. Covers creating views, state management with @Observable, NavigationStack routing, animations, accessibility, performance optimization, Liquid Glass adoption, design…