What is p3a AGENTS.md?

Repository instructions for p3a, firmware for an ESP32 device that displays animated and still pixel art from online and local sources. They describe the hardware, supported media, update model, and development rules.

Use them when working on the p3a firmware, its image sources, display and network behavior, repository commands, or release-related changes.

They provide essential project context and safety rules before changing software that runs on real devices and receives production updates.

How fabkury/p3a configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to fabkury/p3a. 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/fabkury/p3a/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/fabkury/p3a

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/fabkury/p3a/agents-md/github.svg)](https://agentmods.dev/instructions/fabkury/p3a/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/fabkury/p3a/agents-md"><img src="https://agentmods.dev/badge/instructions/fabkury/p3a/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/fabkury/p3a/agents-md"><img src="https://agentmods.dev/badge/instructions/fabkury/p3a/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,357 This file is loaded in full into every session.

When invoked 4,357 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	$0.04357	$0.04357
Opus 5.5	$0.01743	$0.01743
Sonnet 5.5	$0.00871	$0.00871
Haiku 4.5	$0.00436	$0.00436

Measured 1mo ago against content hash 52f0a60b3c00, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

p3a 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 1mo 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 · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents working in this repository. This is the canonical file: CLAUDE.md imports it, so project guidance goes here and only Claude-specific notes go there. It is read at the start of every session, so keep it accurate and keep it short.

Project overview

p3a is an ESP32-P4 Wi-Fi pixel art player. It plays WebP, GIF, PNG, APNG, JPEG, and BMP files, animated and static: GIFs and stickers from Giphy and Klipy, animated artworks from Makapix Club (a pixel art social network), static museum artworks over IIIF and similar image CDNs, artworks fetched from a URL, and local files on the SD card.

Target hardware is the Waveshare ESP32-P4-WIFI6-Touch-LCD-4B: 720x720 IPS display (24-bit, MIPI-DSI), GT911 capacitive touch, 32 MB PSRAM, 32 MB flash, and an ESP32-C6 Wi-Fi 6 co-processor reached through esp_hosted over SDIO.

The firmware is public (Apache 2.0) and runs on real users' devices, which receive updates over the air from GitHub Releases once their owner approves the install in the web UI (nothing installs unattended). Treat main as production.

Ground rules

Never build, flash, or monitor on your own initiative. Do not run idf.py build, idf.py flash, idf.py monitor, or anything else that compiles or flashes the firmware unless the user directly and explicitly asks for it, not even to "check that it compiles". The user does the building and the testing on hardware. A work-stream README may relax this for that stream (docs/jitter/README.md did); such a grant applies only while the user has you working in that stream.
A change is unverified until the user confirms it on the device. Say so plainly. Do not describe untested work as done, working, or verified.
Clarifying questions are always welcome. Ask when different readings of a request would lead to materially different work.

Toolchain and environment

ESP-IDF v5.5.4, target esp32p4, developed on Windows with PowerShell. Setting up a new machine: docs/reference/esp-idf-5.5.4-setup.md.
The ESP32-C6 image network_adapter.bin is a prebuilt binary in components/slave_ota/firmware/; slave_ota flashes it into the P4's slave_fw partition. It is not built by this project.
Activate the IDF environment once per shell session and reuse that session. Re-sourcing the profile for every command leaves stray shells behind.

Read the full file on GitHub · 265 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.

1mo ago Changed · +6 lines · +115 tokens per session 52f0a60b3c00
1mo ago Changed · +1 lines · +96 tokens per session 27ba3c3adc57
2mo ago Changed · +257 lines · +3,973 tokens per session e5f6f489a8de
2mo ago First seen · 1 lines · 173 tokens per session scan A 377f07a57e1e

Subscribe to this mod's changes

p3a AGENTS.md is an instructions file published in the GitHub repository fabkury/p3a (101 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 4,357 tokens to every session, about $0.0174 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 2026-09-01.

Game development Hardware and IoT art embedded esp32 esp32-p4 pico-8 pixel-art

p3a AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
p3a AGENTS.mdfabkury/p3a	Instructions file	101	1mo ago	Apache-2.0	A	4,357	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	today	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

p3a: Instructions file for Codex