What is 11m-game AGENTS.md?

Repository instructions for firmware built on the AK event-driven microcontroller framework, including rules for using its documentation and protecting core source directories.

Use them to start an AK project, create application tasks or drivers, access exact framework APIs, and debug a board through its UART console.

They reduce the risk of guessing framework APIs or changing kernel and hardware files that must remain untouched.

How caotrongphuoc/11m-game configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to caotrongphuoc/11m-game. 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/caotrongphuoc/11m-game/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/caotrongphuoc/11m-game

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/caotrongphuoc/11m-game/agents-md/github.svg)](https://agentmods.dev/instructions/caotrongphuoc/11m-game/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/caotrongphuoc/11m-game/agents-md"><img src="https://agentmods.dev/badge/instructions/caotrongphuoc/11m-game/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/caotrongphuoc/11m-game/agents-md"><img src="https://agentmods.dev/badge/instructions/caotrongphuoc/11m-game/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,746 This file is loaded in full into every session.

When invoked 4,746 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	$0.04746	$0.04746
Opus 5.5	$0.01898	$0.01898
Sonnet 5.5	$0.00949	$0.00949
Haiku 4.5	$0.00475	$0.00475

Measured 17d ago against content hash 4b4ccf14e79f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

11m-game 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 17d 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 · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AK firmware — agent instructions

This project is firmware for the AK (Active Kernel) event-driven MCU framework.

You have access to the ak-docs MCP server. Use it as the source of truth — do not guess AK APIs from memory.

Starting a new project? If this is a fresh/empty workspace (no application/ yet), call start_ak_project first — it downloads the latest base-kit release and gives you the commands to lay it out. Run them, then customize per the steps below.

Before writing or changing any firmware:

Call get_ak_guardrails first. Never modify application/sources/ak/ (kernel), boot/, application/sources/networks/, or application/sources/common/. Build features in application/sources/app/ and application/sources/driver/ only.
For a new task/driver/screen, call get_ak_guide (create-task, create-driver, create-screen, use-timer, isr-bridge, tune-pools) and follow the steps and skeleton exactly.
For any kernel function/macro, call get_ak_api to get the exact signature and arguments. Use search_ak_docs when you don't know the symbol name.

Debugging a running board? All debugging is over the UART console (115200 8N1): call get_ak_guide("debug-uart-shell") first. Capture output non-interactively with python ak-console.py --port <P> --cmd "ver" --cmd "fatal l" (or --watch 15 for live logs), then paste the raw text into analyze_ak_log and follow its Next steps. For display issues, capture --cmd "lcd d" and paste the dump into decode_ak_lcd to see the OLED contents. Run only read-only shell commands on your own; destructive ones (reboot, fatal t/!/@/r, ram r, eps r, flash i, boot r/t, fwu, dbg s) need the engineer's explicit OK.

Hard rules (also returned by get_ak_guardrails):

Handlers must be non-blocking — no delay(), no busy-wait. Use a timer that posts a signal instead.
Tasks communicate only via messages (task_post_*), never direct cross-task calls or foreign-state access. The approved extern instances below do not change this rule.
User signals start at AK_USER_DEFINE_SIG (10); task priorities are LEVEL_1..7 (0 is reserved).
Common message payload ≤ 64 bytes; max 7 references per message; pools are fixed size.

Read the full file on GitHub · 323 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.

17d ago Changed · -1 lines · -7 tokens per session 4b4ccf14e79f
21d ago Changed · +174 lines · +2,641 tokens per session 3a6e579cbe3e
2mo ago First seen · 150 lines · 2,112 tokens per session scan A d1695ba6932d

Subscribe to this mod's changes

11m-game AGENTS.md is an instructions file published in the GitHub repository caotrongphuoc/11m-game (6 stars, last pushed 11d ago), licensed MIT. It adds 4,746 tokens to every session, about $0.0190 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 2026-08-31.

ak-base-kit embedded-systems mcp-server penalty-shootout stm32l151

11m-game AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
11m-game AGENTS.mdcaotrongphuoc/11m-game	Instructions file	6	11d ago	MIT	A	4,746	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

11m-game: Instructions file for Codex