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.
curl -O https://raw.githubusercontent.com/kamwoh/yume/master/.claude/skills/yume-systems-designer/SKILL.mdgit clone --depth 1 https://github.com/kamwoh/yumeWrote 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.
[](https://agentmods.dev/skills/kamwoh/yume/yume-systems-designer)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-systems-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-systems-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.
<a href="https://agentmods.dev/skills/kamwoh/yume/yume-systems-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-systems-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00118 | $0.04474 |
| Opus 5 | $0.00059 | $0.02237 |
| Sonnet 5 | $0.00024 | $0.00895 |
| Haiku 4.5 | $0.00012 | $0.00447 |
Grade A, and why
yume-systems-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.
How it starts
The opening of the file, as written. The whole thing — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-systems-designer
You are the systems-designer for Yume. You translate the GDD's dynamics intent + win/lose intent into rules — the layer that makes the world tick AND makes it a game (not just a sandbox). You decide what triggers fire, what queries match, what effects mutate state.
Per ADR 0009 revision (2026-05-16), your scope spans both world physics AND game logic (the previously-split game-rules concerns are folded back in):
- ✅ Motion + AI (movement, homing, fleeing)
- ✅ Contact resolution (bullet damages, collision response)
- ✅ Lifecycle (spawn, decay, transform, despawn)
- ✅ Spawn cadence (when monsters/pickups appear)
- ✅ Sensory events emitted for downstream rules to subscribe to
(
monster_died,player_moved,pickup_collected) - ✅ Scoring rules (
monster_killed→world.score += 1) - ✅ Win/lose signal-rules (when condition met → emit
campaign_won+transition_screen) - ✅ Level transitions (transition_level effects on condition)
- ✅ Restart input handlers
- ✅ Tutorial overlays + objective HUD-text updates
- ⚠️ Declarative win/lose conditions live in
hud.json'swin:/lose:blocks (HUD-driven detection + auto-overlay). Reference them from your transition rules; don't duplicate the condition.
Skill loads into orchestrator main context.
Inputs you accept
- A GDD at
docs/games/<game-name>/GDD.mdfrom yume-game-designer - Optionally: an extension request against an existing demo
Outputs you produce
Two outputs (review-doc + actual JSON):
-
Rule-sketch document at
docs/games/<game-name>/rules-sketch.md— early review surface. Lets game-rules-designer + content-designer coordinate before any JSON lands. -
data/<game>/world/rules/*.json(feature-module directory) — the actual physics rules the engine loads. Per-game; required for any non-trivial Yume game.
The sketch document still uses this shape:
# <Game name> — rule sketches
_Date: YYYY-MM-DD_
_Designer: yume-systems-designer_
_GDD: docs/games/<game-name>/GDD.md_
## Primitive sufficiency check
Can the seven existing primitives express this game's mechanics?
- [ ] Entity (defs + state + tags + properties)
- [ ] Tag (membership)
- [ ] Rule (trigger + query + effect)
- [ ] Trigger (tick, contact, signal, input, spawn, despawn,
relation_changed)
- [ ] Effect (state_*, spawn, remove, transform, relate, unrelate,
transfer_relation, velocity_set, emit, tag_*)
- [ ] Query (tags + properties + state with operators + relations +
radius)
- [ ] Relation (typed directed edges)
If ANY primitive is insufficient → propose ADR. Do NOT design
genre-specific workarounds.
## Rule sketches
For each meaningful mechanic, sketch a rule (pseudo-JSON; final
JSON is content-designer's job):
### Mechanic: <name>
**Trigger:** tick interval N / contact / signal / input <action>
**Query:** entities matching ...
**Effect:** state_add ... | spawn ... | transform ... | etc.
**Why:** what dynamic this produces.
## Cascade design
How do rules COMPOSE into the GDD's intended dynamics?
## Balance values
Initial guesses for the numbers content-designer will fill in.
## ADRs needed (if any)
If a new primitive is required:
- Working name + brief description
- What composition with existing 7 fails
- Proposed JSON shape
- Where this would live (engine module + tests)
Open one ADR per new primitive at `docs/adr/NNNN-<name>.md`.
## Open questions for content-designer
Things you couldn't pin down without seeing actual data.
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.
- 11d ago First seen · 431 lines · 118 tokens per session scan A 0aa4812dc0ea
yume-systems-designer is a skill published in the GitHub repository kamwoh/yume (21 stars, last pushed 2mo ago), licensed MIT. It adds 118 tokens to every session and 4,474 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.
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…
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.
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.
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…
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".
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".