yume: Skill for Claude Code

.claude/skills/yume-save-policy-designer/SKILL.md

yume-save-policy-designer is a skill for Claude Code from kamwoh/yume. It costs 114 tokens per session (1,977 once invoked), scanned A, original, MIT.

A game-development guide for designing save rules in Yume, deciding which progress, world data, and entities persist after the player reloads a game.

In plain words
What is it for?
It helps create a save_policy.json file, choose persistent world-state keys and entities, define autosave triggers, and plan save-version changes.
Why use it?
It prevents saves from losing important progress, storing unnecessary temporary data, or breaking when the save format changes.

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-save-policy-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-save-policy-designer

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kamwoh/yume/yume-save-policy-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-save-policy-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,977 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 $0.00114 $0.01977
Opus 5 $0.00057 $0.00988
Sonnet 5 $0.00023 $0.00395
Haiku 4.5 $0.00011 $0.00198

Measured 12d ago against content hash 32b7b5474122, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

yume-save-policy-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 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-save-policy-designer/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/yume-save-policy-designer

You are the save policy designer for Yume. Your job: decide what persists across sessions for each game.

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

Why this skill exists

Save/load is universal in shipping games but underspecified per-game. Without a policy specialist, common failure modes:

  • Saves miss critical state (player progress restarts after reload)
  • Saves include too much (every projectile, every tile — saves balloon)
  • No autosave triggers (player rage-quits after losing 30 minutes)
  • Save schema changes silently break old saves
  • Persistent entities don't actually persist across chunks (per ADR 0014)

This skill produces save_policy.json per ADR 0010's schema.

Inputs

  • A GDD at docs/games/<game>/GDD.md (mentions save / progress / achievements / persistence)
  • Optional: world-plan (named NPCs that should persist), level-design (level-transition triggers), economy-design (currencies that should persist)

Outputs

A save policy at data/<game>/save_policy.json (per ADR 0010 schema).

Core questions to answer

1. What world_state keys persist?

Walk through the game's world_state usage. For each key, decide: persist vs reset on new game vs purely runtime.

Examples:

  • current_level — persist (player resumes at correct level)
  • score — persist (long-term progress)
  • tutorial_step — persist (don't re-do tutorial after reload)
  • achievements_unlocked — persist (cross-save persistence)
  • tick — runtime only (reset; engine recomputes)
  • _pending_level_transition — runtime only (engine internal)
  • last_input_action — runtime only

Rule of thumb: persist if the player would feel cheated by losing it.

2. Which entity tags survive?

Per ADR 0014, persistent-tagged entities survive chunk eviction. The save policy further filters which TAGS the engine SERIALIZES.

Typical patterns:

  • named_npc — persist (each NPC has identity + state)
  • shop / landmark / chest — persist (positional + state)
  • pickup / monster / projectile — DON'T persist (transient)
  • terrain / wall — DON'T persist (reload from chunk JSON)

Read the full file on GitHub · 249 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 · 249 lines · 0 tokens per session scan A 32b7b5474122

Subscribe to this mod's changes

yume-save-policy-designer is a skill published in the GitHub repository kamwoh/yume (21 stars, last pushed 2mo ago), licensed MIT. It adds 114 tokens to every session and 1,977 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

godot-engineer

!cat skills/shared/protocols/3d-spatial-foundations.md 2>/dev/null || true !cat skills/shared/game-visual-foundations.md 2>/dev/null || echo "=== Visual Foundations not loaded ===" !cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/game-test-protocol.md 2>/dev/null || true…

buiphucminhtam/forgewright · 52 tokens

game-engineer

Meta-skill for game development that orchestrates specialized engine skills. Routes to the appropriate game engine skill (Unity, Unreal, Godot, Roblox, Phaser 3, Three.js) based on project requirements. Provides unified game development workflow.

buiphucminhtam/forgewright · 52 tokens

self-evolve

Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.

tettethu/VibeGame · 50 tokens

fps-controller

Use when building an FPS, first-person movement, or a 3D character that walks, jumps, and reacts to external forces — production-quality first-person controller with WASD, mouse look, jump, coyote time, jump buffering, air control, and external-velocity handling. Trigger on "FPS", "first-person", "WASD", "character…

SummerEngine/summer-engine-agent · 89 tokens

smoke

Use when authoring a smoke visual effect — a slow-rising column or puff of soft particles built with a noise + density falloff shader on a quad mesh, GPUParticles3D. Trigger on "smoke", "smoke trail", "puff", "chimney smoke", "smoke from a fire", "steam", "fog cloud", "explosion smoke".

SummerEngine/summer-engine-agent · 81 tokens

water-ripple

Use when authoring a water-ripple visual effect — animated normal-distortion ripples on a water plane (or as a Decal) triggered by impacts. Trigger on "water ripple", "ripples on water", "raindrop ripple", "splash ripple", "rain on water", "footstep in puddle", "fish jumps".

SummerEngine/summer-engine-agent · 75 tokens