learn-plugin-docs

A skill that fetches and condenses documentation for Minecraft plugins and mods into a local Markdown reference.

In plain words
What is it for?
Looking up how to configure a Minecraft plugin or mod, including its commands, permission nodes, configuration keys, and placeholders.
Why use it?
It prevents the agent from guessing configuration keys, commands, permissions, or placeholders when documentation may have changed.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/teddy563/mcwrench/learn-plugin-docs
Any agent
npx skills add Teddy563/mcwrench --skill learn-plugin-docs
Clone the repo
git clone --depth 1 https://github.com/Teddy563/mcwrench

Made for: Claude Code, Codex.

Per session 205 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,247 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00205 $0.01247
Opus 5 $0.00102 $0.00624
Sonnet 5 $0.00041 $0.00249
Haiku 4.5 $0.00020 $0.00125

Measured 2d ago against content hash 6fa621f3bdb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-plugin-docs 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.

skills/learn-plugin-docs/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn Plugin Docs

Turn a plugin name or URL into a local, condensed markdown reference, then answer from it.

When to use

Any time you are not confidently current about a specific plugin's config keys, permission nodes, commands, or placeholders. Fetch first, answer second. Never invent config keys.

Procedure

Given an argument like LuckPerms, MythicMobs, https://modrinth.com/plugin/dynmap, or a Hangar slug:

  1. Check the bundled library first, then the cache. ~55 popular plugins are pre-fetched into skills/learn-plugin-docs/library/ (committed, zero-network) and resolved by name/alias via library/registry.json. learn-docs.mjs does this automatically — resolution order is library → _cache/ (7-day) → registry canonical URL → Modrinth/Hangar search. Pass --refresh to bypass the library/cache and re-fetch. If skills/_cache/<slug>/REFERENCE.md already exists and is recent, it is reused.

  2. Resolve the target. If $ARGUMENTS is a URL, infer the host. If it's a name, the script searches Modrinth, then Hangar.

  3. Run the fetcher:

    node "${CLAUDE_PLUGIN_ROOT}/skills/learn-plugin-docs/scripts/learn-docs.mjs" "$ARGUMENTS"
    

    It picks the cheapest adapter for the host (see references/source-routing.md), fetches the authoritative markdown, condenses it, and writes:

    • skills/_cache/<slug>/REFERENCE.md — condensed (Overview, Install, Config keys, Permissions, Commands, Placeholders, Dependencies, Folia, Footguns), with source_url + fetched_at.
    • skills/_cache/<slug>/RAW.md — the full fetched markdown.
  4. Read REFERENCE.md and answer the user's actual question from it. Summarise the key config keys, permissions, and commands, and cite the cache path + source URL.

  5. If the fetch fails (host unknown, network blocked on enterprise installs), tell the user and offer the manual fallback: ask them to paste the relevant docs, or to upload the plugin .jar so you can read plugin.yml (commands/permissions) and bundled config.yml.

Read the full file on GitHub · 83 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2d ago First seen · 83 lines · 205 tokens per session scan A 6fa621f3bdb0

Subscribe to this mod's changes

learn-plugin-docs is a skill published in the GitHub repository Teddy563/mcwrench (1 stars, last pushed 9d ago), licensed MIT. It adds 205 tokens to every session and 1,247 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.

netease-youdao/LobsterAI · 64 tokens

roblox-studio

Build and edit in Roblox Studio via the Roblox Studio MCP the RIGHT way - preflight the Studio connection, do the whole build in a few big executeluau scripts (not dozens of tiny calls), make REALISTIC terrain with the Terrain VOXEL api driven by Perlin noise (NEVER stacked Parts or concentric layers - those give ugly…

XAIHT/Tlamatini · 120 tokens

threejs-animation

Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.

fabioc-aloha/Alex_Skill_Mall · 40 tokens

domain-glossary

Extract a DDD-style ubiquitous language glossary from the current conversation.

kambleakash0/agent-skills · 18 tokens

spec-to-plan

Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices.

kambleakash0/agent-skills · 21 tokens

code-review

Performs a thorough code review of the current changes or a specified file / pull request. Covers correctness, security, performance, readability, and adherence to project conventions. Outputs prioritised, actionable feedback. TRIGGER when the user writes /code-review or asks for a code review, PR review, or feedback…

kambleakash0/agent-skills · 68 tokens