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/hexianweb/third-person-mc/agents-mdgit clone --depth 1 https://github.com/hexianWeb/Third-Person-MCWhat 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 | $0.02908 | $0.02908 |
| Opus 5 | $0.01454 | $0.01454 |
| Sonnet 5 | $0.00582 | $0.00582 |
| Haiku 4.5 | $0.00291 | $0.00291 |
Grade A, and why
Third-Person-MC 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 — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Development Guide for AI Coding Agents
This document provides essential information for AI coding agents working in this repository.
Build, Lint, and Test Commands
Package Manager
This project uses pnpm. Always use pnpm instead of npm or yarn.
Development
pnpm dev # Start development server with hot reload
pnpm build # Build for production
pnpm preview # Preview production build locally
Linting
pnpm lint # Check code for linting errors
pnpm lint:fix # Auto-fix linting issues
Testing
# E2E tests with Playwright (located in tests/ directory)
pnpm test:chrome # Run tests in Chromium (headed mode)
pnpm test:firefox # Run tests in Firefox (headed mode)
pnpm test:safari # Run tests in WebKit/Safari (headed mode)
Running a single test:
npx playwright test tests/browsers.test.js --headed --project=chromium
npx playwright test tests/browsers.test.js:10 --headed # Run specific line
Cleanup
pnpm clean:dist # Remove dist directory
pnpm clean:report # Remove Playwright test reports
Code Style Guidelines
Language & Modules
- Pure JavaScript (no TypeScript) with ES modules (
"type": "module") - Use
.jsextensions explicitly in imports - Use JSDoc comments for type hints where beneficial
Formatting (ESLint - Antfu)
- Style Guide: Follows
@antfu/eslint-configdefaults - Print width: 120 characters
- Indentation: 2 spaces (no tabs)
- Semicolons: None (Never use semicolons)
- Quotes: Single quotes (
') for JS/Vue, single for JSX - Trailing commas: All (Multi-line objects/arrays)
- Arrow parens: Always
- Line endings: CRLF (Windows)
- Plugins:
prettier-plugin-tailwindcssfor class sorting
CRITICAL FORMATTING RULES:
- Respect Existing Style: When modifying a file, mimic the existing formatting (braces, blank lines, sorting) exactly.
- Vue SFC: Do NOT indent top-level content inside
<script setup>or<style>. - Minimal Changes: Do NOT reformat the entire file. Only apply formatting to your specific changes.
- Antfu Nuances: Allow single-line
ifstatements without braces.
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 · 412 lines · 2,908 tokens per session scan A 6134caa224cb
Third-Person-MC AGENTS.md is an instructions file published in the GitHub repository hexianWeb/Third-Person-MC (189 stars, last pushed 1mo ago), licensed MIT. It adds 2,908 tokens to every session, about $0.0145 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.
Other instructions, from other repositories
client AGENTS.md
AGENTS.md instructions for corosolto/client, covering agents.md — porta de entrada, antes de escrever régua ou mexer em asset: docs/licoes.md, o que é este projeto, as duas zonas and as leis da casa.
super-claudio-brothers CLAUDE.md
Instructions for alexconner-79/super-claudio-brothers, covering super claudio brothers — claude code handoff, what this is, project structure, the supabase leaderboard task and what to do.
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
tiptap AGENTS.md
Instructions for ueberdosis/tiptap, covering tiptap, rules, before opening a pr, code style and files.
joint CLAUDE.md
Instructions for clientIO/joint, covering claude.md, project overview, common commands, install dependencies and build distribution files (runs grunt).
qiankun CLAUDE.md
Instructions for umijs/qiankun: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.