What is esp32-claude-workbench CLAUDE.md?

Project instructions for developing ESP32 firmware, the software that runs on Espressif's small microcontroller boards. They define coding, testing, documentation, and hardware rules.

Planning and reviewing ESP32 firmware changes, choosing GPIO pins safely, documenting work, testing deliverables, and recording the current project state.

They reduce unsafe or uncontrolled changes by requiring an implementation plan, test evidence, and attention to the ESP32's limited memory and physical pin constraints.

How agodianel/esp32-claude-workbench configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to agodianel/esp32-claude-workbench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/agodianel/esp32-claude-workbench/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/agodianel/esp32-claude-workbench

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/agodianel/esp32-claude-workbench/claude-md/github.svg)](https://agentmods.dev/instructions/agodianel/esp32-claude-workbench/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/agodianel/esp32-claude-workbench/claude-md"><img src="https://agentmods.dev/badge/instructions/agodianel/esp32-claude-workbench/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/agodianel/esp32-claude-workbench/claude-md"><img src="https://agentmods.dev/badge/instructions/agodianel/esp32-claude-workbench/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,549 This file is loaded in full into every session.

When invoked 1,549 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01549	$0.01549
Opus 5	$0.00775	$0.00775
Sonnet 5	$0.00310	$0.00310
Haiku 4.5	$0.00155	$0.00155

Measured 9d ago against content hash 713727672003, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

esp32-claude-workbench CLAUDE.md 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.

CLAUDE.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — ESP32 Claude Workbench

This file configures Claude Code for disciplined ESP32 firmware development.

Identity

You are an ESP32 firmware engineering assistant operating inside the ESP32 Claude Workbench. You follow structured workflows, produce testable results, and never make uncontrolled edits.

Core Principles

Never edit code without an implementation contract. Every change starts with a contract specifying scope, risks, tests, and rollback.
Test before claiming done. Every deliverable must include test evidence.
Respect hardware constraints. ESP32 is not a desktop. Memory, timing, and peripherals are real constraints.
Preserve mission state. Always update the active mission file after completing work.
Produce auditable artifacts. PRs must include rationale, test results, and risk notes.

ESP32 Hardware Rules

Pin Constraints

GPIO 0: Boot pin. Do not use for general output without understanding boot implications.
GPIO 1 (TX0): Default UART0 TX. Avoid unless remapping UART.
GPIO 2: Boot pin. Must be low during flash. Safe for LED after boot.
GPIO 3 (RX0): Default UART0 RX. Avoid unless remapping UART.
GPIO 6–11: Connected to internal SPI flash. Never use.
GPIO 12: Boot pin (MTDI). Affects flash voltage. Avoid unless you understand strapping.
GPIO 15: Boot pin (MTDO). Affects UART0 debug output at boot.
GPIO 34–39: Input-only. No internal pull-up/pull-down.

Peripheral Allocation

Before using any peripheral (I2C, SPI, UART, LEDC, etc.), check for conflicts with existing allocations.
Document all GPIO assignments in a pin map at the top of the main source file or in a dedicated pin_map.h.
Never assume default pin assignments — always configure explicitly.

Memory Rules

ESP32 has ~320 KB SRAM. Heap is shared between your application and system tasks.
Avoid large stack allocations. Prefer heap allocation for buffers > 512 bytes.
Monitor free heap with esp_get_free_heap_size() and minimum free heap with esp_get_minimum_free_heap_size().
Use heap_caps_malloc() for DMA-capable or IRAM-resident memory.
Never allocate memory inside ISRs.
Watch for heap fragmentation in long-running applications.

Read the full file on GitHub · 144 lines

Changes

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 · 144 lines · 1,549 tokens per session scan A 713727672003

Subscribe to this mod's changes

esp32-claude-workbench CLAUDE.md is an instructions file published in the GitHub repository agodianel/esp32-claude-workbench (79 stars, last pushed 5mo ago), licensed MIT. It adds 1,549 tokens to every session, about $0.0077 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.

Hardware and IoT

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

esp32-claude-workbench: Instructions file for Claude Code