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/teddy563/mcwrench/agents-mdgit clone --depth 1 https://github.com/Teddy563/mcwrenchWhat 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 | $0.01134 | $0.01134 |
| Opus 5 | $0.00567 | $0.00567 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
mcwrench 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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcwrench — guidance for Codex & Antigravity (and other AGENTS.md-aware agents)
This repo is mcwrench, a general-purpose, gamemode-agnostic Minecraft server config & operations assistant. The same skills work in OpenAI Codex, Google Antigravity, Claude Code, Claude.ai, and Gemini CLI.
Skills discovery (Codex & Antigravity)
Skills live in .agents/skills/, which is a symlink to skills/ (the single source of
truth — both Codex and Antigravity follow symlinked skill folders, and .agents/skills/ is
Antigravity's native skills path). Each folder has a SKILL.md with name + description.
Invoke a skill explicitly (Codex $skill-name, e.g. $audit-config) or let the agent auto-select
by description. Antigravity also exposes the .agents/workflows/ files as slash commands
(/audit, /learn, /perf, /perms, /proxy, /bootstrap, /panel, /gamemode, /conflicts,
/brand, /profile, /create, /stack, /format, /diagnose, /health, /upgrade, /skript,
/help) and reads
.agents/rules/mcwrench.md.
| Skill | Use for |
|---|---|
minecraft-server-router |
Always-on hub for ANY Minecraft server-admin topic; routes to a specialist. |
audit-config |
Lint a config tree for footguns, performance, and security; --write-profile + check-conflicts.mjs. |
server-doctor |
Day-2 ops (read-only): diagnose a crash/log, grade server health, plan a 26.1/Java-25 upgrade. parse-log.mjs + check-plugin-versions.mjs. |
performance-tuning |
Lag / TPS / MSPT / OOM; Spark profiling; Aikar's flags; view/sim distance; entity & chunk tuning. |
permissions-helper |
LuckPerms groups, tracks, contexts, meta; Vault; node conventions. |
proxy-network |
Velocity/Bungee modern forwarding and the forwarding.secret handshake. |
gamemode-stacks |
Canonical plugin stacks for 25 archetypes (SMP, skyblock, prison, factions, towny, minigames, RPG/MMO, anarchy, creative, KitPvP, lifesteal). |
server-branding |
Brand kit from a name + vibe: identity, MOTD (right format per plugin), ranks, store/Discord copy, tone presets, MiniMessage↔legacy helper. |
gamemode-designer |
Invent + score original gamemodes (combine archetypes + one twist), then plan a fun server locally. The foundry behind /create; plans only, no live connectors. |
new-server-bootstrap |
Greenfield Paper/Velocity setup; Fill v3 Paper downloader; Java-25 + Aikar startup; starter configs. |
pterodactyl-ops |
Pterodactyl/Pelican panel: RCON, Xmx/AlwaysPreTouch OOM, non-atomic backups, client API. |
skript-author |
Write/debug Skript; fetch live syntax from Skript Hub. |
learn-plugin-docs |
Fetch + condense ANY plugin's docs; 64 popular plugins pre-loaded in library/; --pin stores permanently. |
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.
- 2d ago First seen · 57 lines · 1,134 tokens per session scan A 2e388bb224fc
mcwrench AGENTS.md is an instructions file published in the GitHub repository Teddy563/mcwrench (1 stars, last pushed 9d ago), licensed MIT. It adds 1,134 tokens to every session, about $0.0057 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
ableton-11-mcp-for-windows-codex-and-antigravity AGENTS.md
AGENTS.md instructions for cafeTechne/ableton-11-mcp-for-windows-codex-and-antigravity, covering abletonmcp, architecture, environment setup, prerequisites and installation.
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
agent-skills AGENTS.md
AGENTS.md instructions for racastellanosm/agent-skills, covering agents.md, 1. vision & architectural invariants, 2. repository architecture & layout, 3. harness support & installation paths and 4. scripting & tooling guardrails.
cerebro-inevita GEMINI.md
Instructions for gabrielzucco/cerebro-inevita: Leia CLAUDE.md por inteiro: ele é o contrato canônico de operação deste cérebro. As skills portáveis vivem em .agents/skills/. Ative a skill adequada por linguagem natural; na primeira sessão, use comecar. Se as skills ainda não aparecerem no Gemini CLI, rode /skills…
Cerebro AGENTS.md
Instructions for AgenticFirst/Cerebro, covering cerebro — agent context, read before touching integrations, project layout, conventions a fresh agent would otherwise miss and running locally.
ZipAI CLAUDE.md
Claude Code instructions for nickdesi/ZipAI, covering claude.md — zipai: ultra-dense token optimizer, rules, 1. zero filler, 2. ambiguity and 3. prompt caching.