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 agentmods add instructions/mazipan/mini-games/agents-mdgit clone --depth 1 https://github.com/mazipan/mini-gamesWrote 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/instructions/mazipan/mini-games/agents-md)<a href="https://agentmods.dev/instructions/mazipan/mini-games/agents-md"><img src="https://agentmods.dev/badge/instructions/mazipan/mini-games/agents-md.svg" alt="Measured on agentmods" 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 | $0.04077 | $0.04077 |
| Opus 5 | $0.02039 | $0.02039 |
| Sonnet 5 | $0.00815 | $0.00815 |
| Haiku 4.5 | $0.00408 | $0.00408 |
Grade A, and why
mini-games 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 3d 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mini-games — AI Coding Guide
Project Overview
A collection of free, browser-based mini games built with Eleventy (SSG), Tailwind CSS, and Nunjucks templates. Each game is a self-contained page.
Tech Stack
- Eleventy 3.x — static site generator, config in
eleventy.config.js - Nunjucks — template engine for layouts and partials
- Tailwind CSS v4 — utility-first CSS, configured via
src/css/main.css(@theme) - PostCSS + @tailwindcss/postcss — CSS pipeline, config in
postcss.config.js - Prettier — code formatter, config in
.prettierrc - Lefthook — pre-commit hooks, config in
lefthook.yml - Commitlint — conventional commit enforcement
- Bun — package manager and script runner
Development Commands
bun run dev # start dev server (Eleventy + Tailwind watch)
bun run build # production build
bun run format # format all files with Prettier
bun run format:check # check formatting without writing
bun run generate:og # re-render public/og-image.svg → public/og-image.png
bun run generate:favicon # regenerate all per-game favicons in public/
Project Structure
public/ # static assets copied as-is to _site/ root
og-image.svg # source OG image (1200×630, edit this)
og-image.png # pre-rendered PNG (committed, copied at build)
favicon.png # site-wide fallback favicon (🎮)
favicon-[slug].png # per-game emoji favicons (one per game)
google…html # Google Search Console verification file
scripts/
generate-og-image.mjs # renders og-image.svg → og-image.png
generate-favicon.mjs # generates all favicon-[slug].png from games.js icons
src/
_data/
site.js # site-wide metadata (title, description, url)
games.js # array of all games with metadata
_includes/
layouts/
base.njk # base HTML wrapper (head, full SEO meta, CSS)
game.njk # game page layout (nav, full SEO meta, per-game favicon)
partials/
header.njk # site header with nav
footer.njk # site footer
hero.njk # landing page hero section
features.njk # USP/features section
games-list.njk # games grouped by category
css/
main.css # Tailwind v4 entry point (@import "tailwindcss" + @theme)
games/
[slug]/
index.njk # individual game page
index.njk # homepage
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.
- 3d ago First seen · 366 lines · 4,077 tokens per session scan A 7785fd849ecf
mini-games AGENTS.md is an instructions file published in the GitHub repository mazipan/mini-games (5 stars, last pushed 1mo ago), licensed MIT. It adds 4,077 tokens to every session, about $0.0204 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 2026-08-31.
Other instructions, from other repositories
GameDesignOS AGENTS.md
Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
Cities2-MCP AGENTS.md
Instructions for mayor-modder/Cities2-MCP, covering agent rules, workspace safety, commit and pr safety, public-facing writing and merge and release gates.