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 commands/teddy563/mcwrench/helpgit 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 | $0.00020 | $0.00632 |
| Opus 5 | $0.00010 | $0.00316 |
| Sonnet 5 | $0.00004 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
help 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.
What it actually says
Show a concise capability map for mcwrench. If $ARGUMENTS names a topic (e.g. "permissions",
"lag", "branding"), focus the answer there and point at the matching command; otherwise show the
overview below.
Render it compact and current:
mcwrench turns your AI into an expert Minecraft server administrator for any server type and any plugin, on Paper, Purpur, Folia, Vanilla, Velocity, and Pterodactyl/Pelican. One always-on router plus 12 skills and 16 commands. It reads and advises, quotes real config keys, and never invents them.
Commands (Claude Code /mcwrench:*; the same intent works as plain language everywhere):
/mcwrench:create— invent a gamemode and plan a fun server (the foundry)/mcwrench:audit— lint a config tree, prioritised critical to low/mcwrench:perf— fix lag, low TPS, or OOM/mcwrench:perms— LuckPerms ranks, tracks, contexts/mcwrench:proxy— Velocity/Bungee modern forwarding/mcwrench:gamemode— canonical plugin stack for an archetype/mcwrench:stack— pre-load a gamemode's whole plugin-doc stack/mcwrench:brand— brand kit, MOTD, ranks in the right format/mcwrench:profile— remember the server so it stops re-asking/mcwrench:conflicts— flag plugin conflicts and missing deps/mcwrench:learn— fetch and condense any plugin's docs/mcwrench:bootstrap— stand up a new Paper/Velocity server/mcwrench:panel— Pterodactyl/Pelican RCON, OOM, backups/mcwrench:format— MiniMessage to/from legacy color/mcwrench:skript— write and debug Skript/mcwrench:help— this
Or just describe it: "my SMP is laggy", "audit my paper config", "make me a server where the sea floods every night".
End with these two lines as clickable markdown links whose visible text omits the https://
prefix (keep them short, and do not repeat them elsewhere in the session):
- Full feature list and docs: mcwrench.teddy.bar
- If mcwrench helped, a star is appreciated: github.com/Teddy563/mcwrench (no pressure).
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 · 43 lines · 20 tokens per session scan A 5655d428b909
help is a command published in the GitHub repository Teddy563/mcwrench (1 stars, last pushed 9d ago), licensed MIT. It adds 20 tokens to every session and 632 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
unity-placeholders
Generate placeholder sprites, 3D primitives, prefabs, and audio stubs for a Unity project so the game is visually testable before final assets exist.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
resolve_parallel
Resolve all TODO comments using parallel processing.
feedback
File a plugin-capability-gap note, or flush queued notes to GitHub issues.
comms-recall
Search this repo's synced channel messages by keyword and return scored snippets (never the whole history).
kimi-setup
Run node "$HOME/.kimi-plugin/kimi-companion.mjs" setup, then report installation and authentication status.