skript-author

skript-author is a skill for Claude Code, Codex from Teddy563/mcwrench. It costs 155 tokens per session (793 once invoked), scanned A, original, MIT.

A guide for writing, debugging, and explaining Skript files for Minecraft servers. Skript is a plain-English scripting plugin, and its add-ons provide extra syntax for features such as NBT data, configuration files, holograms, and Java access.

In plain words
What is it for?
Use it to create or repair .sk scripts, custom commands and events, permissions, timed actions, player variables, shops, economies, and scripts that use add-ons such as SkBee or skript-yaml.
Why use it?
It helps identify which syntax and add-on a script needs and explains how events, conditions, effects, expressions, and variables fit together. It also reduces the risk of breaking live server data during reloads.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the mcwrench plugin — 13 skills, 19 commands, 2 agents shipped together

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/skript-author
Any agent
npx skills add Teddy563/mcwrench --skill skript-author
Clone the repo
git clone --depth 1 https://github.com/Teddy563/mcwrench

Made for: Claude Code, Codex.

Or install mcwrench, the plugin that ships this one along with the rest of its 13 skills, 19 commands, 2 agents.

Wrote 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.

agentmods badge for skript-author

README.md
[![agentmods](https://agentmods.dev/badge/skills/teddy563/mcwrench/skript-author.svg)](https://agentmods.dev/skills/teddy563/mcwrench/skript-author)
Your own site
<a href="https://agentmods.dev/skills/teddy563/mcwrench/skript-author"><img src="https://agentmods.dev/badge/skills/teddy563/mcwrench/skript-author.svg" alt="Measured on agentmods" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 793 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 $0.00155 $0.00793
Opus 5 $0.00077 $0.00396
Sonnet 5 $0.00031 $0.00159
Haiku 4.5 $0.00015 $0.00079

Measured 4d ago against content hash 88dfdf24668d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skript-author 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fetch-skripthub.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skript-author/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skript Author

Help with Skript — the plain-English scripting plugin (docs.skriptlang.org) and its addons.

Model (orient before writing)

  • A script is events containing conditions, effects, and expressions:
    on right click on a sign:
        if player has permission "shop.use":
            give player 1 diamond
    
  • Addons add syntax: SkBee (NBT, bound, recipes), skript-reflect (Java reflection), SkQuery, skript-yaml (config files), SkRayFall (citizens/holograms). Identify which addon a needed syntax belongs to before using it.
  • Variables: {var} (per-server), {var::%player's uuid%} (list/per-player). Persisted to variables.csv/DB. Reload carefully (below) or you lose in-flight variables.

Reload-safely workflow (critical on live shops/economies)

  • After editing a .sk, run /sk reload <script> (or /sk reload all). Editing the file on disk does nothing until reloaded.
  • A bad reload can drop variables defined this session. On production: back up variables.csv/the variable DB first, reload a single script (not all), and watch the console for parse errors.
  • Parse errors leave the script unloaded — the whole .sk stops working, not just the bad line.

Fetch live syntax (don't guess)

Skript Hub exposes a JSON syntax API. To pull exact syntax for core Skript or an addon:

node "${CLAUDE_PLUGIN_ROOT}/skills/skript-author/scripts/fetch-skripthub.mjs" --addon SkBee
node "${CLAUDE_PLUGIN_ROOT}/skills/skript-author/scripts/fetch-skripthub.mjs" --search "give"

It queries https://skripthub.net/api/v1/addonsyntaxlist/, filters by addon or search term, and writes a condensed reference to skills/_cache/skripthub/<slug>.md. Read that, then write syntax that matches the installed addon/version — do not invent syntax patterns. (The API is undocumented and may rate-limit; the script caches aggressively.)

Method

  1. Restate the goal as event → conditions → effects.
  2. Identify required addons; fetch their syntax via the script above if unsure.
  3. Write the .sk, then tell the user to /sk reload it and check console for parse errors.
  4. For shops/economies touching money or items, warn about the reload/variable footgun first.

Read the full file on GitHub · 63 lines

Files

What ships with it

1 file 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. 4d ago First seen · 63 lines · 155 tokens per session scan A 88dfdf24668d

Subscribe to this mod's changes

skript-author is a skill published in the GitHub repository Teddy563/mcwrench (1 stars, last pushed 11d ago), licensed MIT. It adds 155 tokens to every session and 793 once invoked, about $0.0008 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

ai-behavior-trees-utility-ai

Build a production behavior-tree runtime (Blackboard, action/condition leaves, sequence/selector/parallel composites, decorators) and a Utility AI system (response curves — linear, exponential, sigmoid, quadratic — considerations, and action evaluators), plus hybrid BT-drives-Utility agents. Use when implementing a…

gamedev-skills/awesome-gamedev-agent-skills · 158 tokens

camera-systems

Build game cameras that feel good — 2D follow with a deadzone, look-ahead, smoothing, and level-bounds clamping; 3D third-person orbit with collision and first-person look; plus multi-target framing and a shake hook. Engine-neutral techniques that pair with the engine's camera node and rigs like Unity Cinemachine or…

gamedev-skills/awesome-gamedev-agent-skills · 127 tokens

create-game-assets

Plan, generate, source, normalize, and validate cohesive visual game assets. Use for art direction, style bibles, sprites, tilesets, backgrounds, UI art, icons, textures, concept art, or 3D asset briefs.

gamedev-skills/awesome-gamedev-agent-skills · 52 tokens

game-ai

Design NPC and enemy decision-making with finite state machines, behavior trees, steering behaviors, and A pathfinding — engine-neutral algorithms that pair with the detected engine's navigation API. Use when building enemy AI, an FSM or behavior tree, steering/flocking, or pathfinding, or when the user mentions state…

gamedev-skills/awesome-gamedev-agent-skills · 85 tokens

game-feel

Add "juice" and game feel that makes actions satisfying — screen shake, hit-stop/freeze frames, tweened/eased motion, squash & stretch, knockback, and layered audio-visual feedback — as engine-neutral techniques that pair with the detected engine's tween, particle, and camera APIs. Use when the user mentions game…

gamedev-skills/awesome-gamedev-agent-skills · 116 tokens