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.
npx skills add SummerEngine/summer-engine-agent --skill design-levelgit clone --depth 1 https://github.com/SummerEngine/summer-engine-agentWrote 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/summerengine/summer-engine-agent/design-level)<a href="https://agentmods.dev/skills/summerengine/summer-engine-agent/design-level"><img src="https://agentmods.dev/badge/skills/summerengine/summer-engine-agent/design-level/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/summerengine/summer-engine-agent/design-level"><img src="https://agentmods.dev/badge/skills/summerengine/summer-engine-agent/design-level.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.03309 |
| Opus 5 | $0.00035 | $0.01655 |
| Sonnet 5 | $0.00014 | $0.00662 |
| Haiku 4.5 | $0.00007 | $0.00331 |
Grade A, and why
design-level 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 9d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-level — Design One Level
Overview
A level is a controlled sequence of player experiences in physical space. Layout, pacing, encounters, secrets, and reward gating must work together — a "fun layout" with a flat pacing curve still feels boring. This skill walks the six design beats of a single level and drops a node-tree skeleton ready for summer_create_scene.
Core principle: A level has a pacing curve and a teaching arc. If you can't draw the tension graph and name what the player learned by the end, the level isn't designed yet.
Steps
1. Pin the level type
Ask exactly one question:
What kind of level? Pick one: tutorial / hub / combat encounter / boss / exploration / puzzle / stealth / platforming-challenge / mixed.
Each type has different beats. Don't blend types in v1 — a "boss room with stealth and puzzles" is three levels poorly squeezed into one.
2. Read context
If .summer/GameSoul.md exists, read it. The level must serve the brief's core loop and the three mechanics.
Read .summer/GameSoul.md
If .summer/mechanics/ exists, list the mechanics. Quote them back:
Brief says mechanics are: dash, parry, double-jump. This level should exercise at least one and ideally combine two.
3. Define the teaching / experience goal
Ask plain:
What does the player know by the end of this level that they didn't at the start?
Tutorial-level answer: "How to dash." Combat-encounter answer: "That parrying converts damage to mana, and that big enemies need parry, not dodge." Exploration answer: "That this region's secrets are hidden behind double-jumpable gaps."
If the user can't answer, the level has no purpose. Say it:
If there's no answer to that question, the level is filler. Either give it a teaching goal, give it a failure-state goal (the player must die here to progress), or merge it into the next level.
4. Sketch the pacing curve
Draw it as text. Five beats, intensity 0-10:
Intro Build Peak Release Hook
2 → 5 → 8 → 3 → 6
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.
- 9d ago First seen · 281 lines · 70 tokens per session scan A ea3128a7ae24
design-level is a skill published in the GitHub repository SummerEngine/summer-engine-agent (59 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 3,309 once invoked, about $0.0003 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
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.
artist-self-evolve
Distill stable art-generation patterns from a completed project, so future projects produce comparable assets without re-discovering the prompts. Lead-dispatched only — orchestrator invokes this skill from its self-evolve flow with a game-slug message; do not self-trigger.
vibegame-build
Run VibeGame's standard end-to-end game development workflow with reviewer gates. Use when the user wants to create a game from zero or evolve an existing game across multiple stages.
vibegame-start
Resume a VibeGame orchestrator session after vibegame start. Use at the beginning of a Claude or Codex session to inspect team runtime state, repair missing persistent members, load goal and GDD context, inspect tasks, and ask the user what to do next.
vibegame-edit
Iterate broadly on an existing game, on top of vibegame-build. Use when the user asks to change an existing game's art style, genre, or core rules. Not for local tuning such as numbers or game feel. Orchestrator only.
hearth-feel
Make a Hearth game feel good, not just run — the juice stack (hit-stop, screen shake, flash, particle bursts, layered sound), tween easing, camera effects, anticipation/recovery animation idioms, game-UX conventions (menus, pause, onboarding, difficulty, save etiquette), effect-asserting playtests, and the quality bar…