yume: Skill for Claude Code

.claude/skills/yume-screen-flow-designer/SKILL.md

yume-screen-flow-designer is a skill for Claude Code from kamwoh/yume. It costs 150 tokens per session (3,664 once invoked), scanned A, original, MIT.

A design guide for a Godot game’s shell screens, such as the title menu, pause menu, settings, save selection, game-over, and credits screens. Godot is a game engine, and the screens are declared as JSON rather than built directly in code.

In plain words
What is it for?
Use it to decide which shell screens a game needs, describe their buttons and labels, define navigation and state changes, and produce a screen design plus a screens.json file.
Why use it?
It keeps menus and other non-gameplay screens organized and consistent with the project’s design rules. It also helps prevent a game from launching straight into gameplay without a complete menu flow.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

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-flow-designer/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-flow-designer

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kamwoh/yume/yume-screen-flow-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-screen-flow-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,664 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 $0.00150 $0.03664
Opus 5 $0.00075 $0.01832
Sonnet 5 $0.00030 $0.00733
Haiku 4.5 $0.00015 $0.00366

Measured 11d ago against content hash 9268d0a75f24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

yume-screen-flow-designer 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 11d 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-flow-designer/SKILL.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/yume-screen-flow-designer

You are the screen flow designer for Yume. Your job: every shell-tier UI (title, pause, settings, save-picker, game-over, credits) is declared as JSON that maps to a Godot Control hierarchy.

This skill loads into the orchestrator's main context (Tier 2.6 — no subagent spawn).

Why this skill exists

Without a screen-flow specialist, games either:

  • Skip the shell entirely (auto-launch into gameplay; no title; no pause) — feels like a prototype, not a complete game
  • Hand-author screens via GDScript (violates Invariant #1)
  • Throw all UX into one screens.json without structure (sprawl)

This skill produces screens.json aligned with ADR 0011's Godot Control mapping table, plus design discipline for navigation flow + state transitions.

Inputs

  • A GDD at docs/games/<game>/GDD.md (mentions menus / pause / save / game-over / credits)
  • Optional: world-plan, level-design (for game-over conditions, save trigger points)

Outputs

A screens design at docs/games/<game>/screens-design.md, plus the final screens.json at data/<game>/screens.json.

Core questions to answer

  1. What screens does this game need? Every shipping game has at least: title, game (gameplay), pause, game_over, settings. Some add: save_picker, credits, options, level_select.

  2. What's the navigation graph? Title → game (new game / continue) Game → pause (escape key) → resume / save / settings / quit Settings → back to wherever opened it Game → game_over → restart / title

  3. For each screen, what elements appear? Use ADR 0011's element-type → Godot-node mapping table. Don't invent new types unless a real game needs one.

  4. What effect chain fires on each button? Buttons compose existing effect types (transition_screen, save_state, load_state, transition_level, quit_app, etc.).

  5. Modal or replace? Pause = modal over game (game stays under, frozen). Settings opened from pause = modal over pause. Title → game = replace.

Read the full file on GitHub · 391 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. 11d ago First seen · 391 lines · 0 tokens per session scan A 9268d0a75f24

Subscribe to this mod's changes

yume-screen-flow-designer is a skill published in the GitHub repository kamwoh/yume (21 stars, last pushed 2mo ago), licensed MIT. It adds 150 tokens to every session and 3,664 once invoked, about $0.0007 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.