yume: Skill for Claude Code

.claude/skills/yume-screen-author/SKILL.md

yume-screen-author is a skill for Claude Code from kamwoh/yume. It costs 170 tokens per session (3,806 once invoked), scanned A, original, MIT.

A tool for turning a wireframe image into an interactive in-game screen, such as an inventory, pause menu, settings page, title menu, or ending screen.

In plain words
What is it for?
Use it to author entries in screens.json from wireframes and connect the screen's interactive elements.
Why use it?
It helps make the finished screen match the reference layout while ensuring its buttons and other controls work.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is kamwoh/yume's own configuration. It tells Claude Code how to work on yume itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything yume configures →

View source ↗ kamwoh/yume
Reuse

Borrowing it

Nothing to install: this file belongs to kamwoh/yume. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kamwoh/yume/master/.claude/skills/yume-screen-author/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kamwoh/yume

Made for: Claude Code.

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 yume-screen-author

README.md
[![agentmods](https://agentmods.dev/badge/skills/kamwoh/yume/yume-screen-author/github.svg)](https://agentmods.dev/skills/kamwoh/yume/yume-screen-author)
Your own site
<a href="https://agentmods.dev/skills/kamwoh/yume/yume-screen-author"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-screen-author/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for yume-screen-author

Your own site · 80×15
<a href="https://agentmods.dev/skills/kamwoh/yume/yume-screen-author"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-screen-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00170 $0.03806
Opus 5 $0.00085 $0.01903
Sonnet 5 $0.00034 $0.00761
Haiku 4.5 $0.00017 $0.00381

Measured 12d ago against content hash 96a4f6c6b09f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

yume-screen-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 12d 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.

.claude/skills/yume-screen-author/SKILL.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/yume-screen-author

STABLE — 2D fit-fit pipeline (confirmed 2026-05-24). This skill

  • its harness (compose_screen, wireframe_to_screen) is locked. Modifying the workflow requires an ADR + scenario regression tests. Active work on Yume's 3D map/world pipeline lives at /yume-map-author and is NOT bound by this status.

Note: the live screens.json per-game CONTENT can keep evolving. Stable means "the harness produces JSON correctly." Per-game UX iteration is normal authoring, not a harness change.

You are the screen author for Yume. You read a wireframe image of a modal or full-cover UI and produce a fit-fit screen entry for that game's screens.json — meaning the in-game screen matches the wireframe pixel-for-pixel (modulo the wireframe→viewport scale) AND its interactive elements wire correctly.

This is the sibling skill to yume-hud-author. Same harness pattern, broader vocabulary, extra validation. The deterministic surface lives at tools/visual_layout/wireframe_to_screen.py.

Why this skill exists (vs yume-hud-author)

  • HUD = always-on overlay during gameplay. Read-only display (vitals, minimap, objective, hotbar). Narrow element catalog: 6 types, all non-interactive.
  • Screen = modal or full-cover UI gated by player input (inventory open with I, pause with Esc, settings menu, title). Broader catalog: 13 types including button, slider, checkbox, option_button — interactive elements with effect chains.

Screens are the bigger semantic surface. A button click can fire any effect type the engine supports (state_set, transition_screen, emit, play_sound, ...). The skill's job is to wire those chains correctly WITHOUT inventing actions outside what the manifest allows.

When to invoke

  • A compose_screen.py run that needs to convert a wireframe → screen entry (the normal authoring path)
  • Iterating on an existing screen — re-runs replace the entry identified by screen_id
  • New screen — first time a game adds e.g. an inventory or pause UI

Read the full file on GitHub · 365 lines

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. 12d ago First seen · 365 lines · 170 tokens per session scan A 96a4f6c6b09f

Subscribe to this mod's changes

yume-screen-author is a skill published in the GitHub repository kamwoh/yume (21 stars, last pushed 2mo ago), licensed MIT. It adds 170 tokens to every session and 3,806 once invoked, about $0.0009 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.