What is chiplab AGENTS.md?

A repository guide for Chiplab, a service that runs compiled microcontroller firmware on virtual versions of real boards and captures serial output. It covers setup and examples for several embedded-software frameworks.

It helps install and connect Chiplab, choose a board example, upload compiled firmware, run it, and inspect its UART output.

It explains how to connect the service and verify firmware without requiring immediate access to physical hardware.

How veecle/chiplab configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to veecle/chiplab. 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/veecle/chiplab/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/veecle/chiplab

Made for: Codex, OpenCode.

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/veecle/chiplab/agents-md/github.svg)](https://agentmods.dev/instructions/veecle/chiplab/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/veecle/chiplab/agents-md"><img src="https://agentmods.dev/badge/instructions/veecle/chiplab/agents-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/veecle/chiplab/agents-md"><img src="https://agentmods.dev/badge/instructions/veecle/chiplab/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,123 This file is loaded in full into every session.

When invoked 2,123 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	$0.02123	$0.02123
Opus 5.5	$0.00849	$0.00849
Sonnet 5.5	$0.00425	$0.00425
Haiku 4.5	$0.00212	$0.00212

Measured 15d ago against content hash 3b1e50d48a60, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chiplab AGENTS.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 15d 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.

AGENTS.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Machine-readable guide for AI coding agents working in this repository.

What is Chiplab

Chiplab simulates firmware on virtual instances of real microcontrollers: upload a compiled ELF, run it on a named virtual board, read back the captured UART output. (See the README for the human-facing pitch.)

MCP endpoint: https://chiplab.veecle.ai/mcp
Account / sign-in: https://veecle.ai (self-serve; free tier, no credit card)

This repo ships ready-to-run examples for every supported board, grouped by framework — currently bare-metal (vendor-HAL / direct-register), embassy-rust (the Embassy async runtime), zephyr-os (C on the Zephyr RTOS, built with west), freertos (C on the FreeRTOS kernel, built with make), and threadx (C on the Eclipse ThreadX kernel, built with make), each documented in examples/<framework>/. A user can open this repo, connect their agent to Chiplab, and say "install Chiplab and test it on <board>" — everything an agent needs to do that is below.

1. Install / connect Chiplab

Ensure the user has a veecle.ai account (self-serve sign-up; no manual provisioning).
Add the Chiplab MCP server to the host agent. Per-client configuration is in the README. The endpoint is https://chiplab.veecle.ai/mcp; use chiplab as the server name.
Complete sign-in in the browser when prompted.

2. Verify the connection

Call Chiplab's discovery/help tool with no arguments. A successful response returns an overview of Chiplab. Always call it first in a session — it carries chip-specific gotchas and validated fixes.

3. Pick the example for the board you want

Examples live at examples/<framework>/<board>/. Do not hardcode the board or framework list here — discover it:

Call the discovery/help tool for the current set of supported boards and their identifiers (it is authoritative and may be ahead of this repo).
For the board↔framework↔example mapping in this repo, read supported-boards.md — the single source of truth (see its Board key column).

Read the full file on GitHub · 164 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.

15d ago Changed · +14 lines · +187 tokens per session 3b1e50d48a60
2mo ago First seen · 150 lines · 1,936 tokens per session scan A c9d0b2035349

Subscribe to this mod's changes

chiplab AGENTS.md is an instructions file published in the GitHub repository veecle/chiplab (18 stars, last pushed 2d ago), licensed MIT. It adds 2,123 tokens to every session, about $0.0085 per session on Opus 5.5. 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 agent agentic-ai hardware software software-engineering virtualization

chiplab AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
chiplab AGENTS.mdveecle/chiplab	Instructions file	18	2d ago	MIT	A	2,123	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

chiplab: Instructions file for Codex