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 lightblink/cocos-creator-local-mcp --skill cocos-level-content-designgit clone --depth 1 https://github.com/lightblink/cocos-creator-local-mcpWrote 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/lightblink/cocos-creator-local-mcp/cocos-level-content-design)<a href="https://agentmods.dev/skills/lightblink/cocos-creator-local-mcp/cocos-level-content-design"><img src="https://agentmods.dev/badge/skills/lightblink/cocos-creator-local-mcp/cocos-level-content-design/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/lightblink/cocos-creator-local-mcp/cocos-level-content-design"><img src="https://agentmods.dev/badge/skills/lightblink/cocos-creator-local-mcp/cocos-level-content-design.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 | $0.00079 | $0.00955 |
| Opus 5 | $0.00039 | $0.00477 |
| Sonnet 5 | $0.00016 | $0.00191 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
cocos-level-content-design 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 10d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cocos Level Content Design
Overview
Use this skill to turn mechanics into paced, testable content. The output should define how levels teach, vary, combine, and pressure the player without relying on random content volume.
This skill coordinates with game design, balance, scene assembly, and QA.
Core Workflow
- Identify the content unit.
- Choose the level, wave, room, puzzle, mission, run segment, or encounter as the smallest authored unit.
- Define level grammar.
- List verbs, hazards, enemies, pickups, spaces, timers, objectives, and constraints.
- Define which combinations are legal, teachable, and readable.
- For procedural or randomized content, define the grammar before generation: allowed modules, banned combinations, spacing rules, difficulty budget, pacing beats, and fairness constraints.
- Sequence learning.
- Introduce one new idea at a time.
- Provide a safe read, a basic use, a pressured use, and a combination use when possible.
- Pace intensity.
- Alternate learning, mastery, pressure, reward, and rest.
- Control density, speed, timer pressure, enemy mix, and resource scarcity.
- Build reusable data.
- Represent levels as tables, JSON, prefabs, blueprints, or scene variants that Cocos can consume.
- Use procedural rules, seedable generators, weighted pools, and validation passes when variation is required. Do not replace content design with unconstrained random placement.
- Define acceptance tests.
- State what the player should understand, feel, and accomplish in each content unit.
Content Deliverables
For substantial tasks, return:
- Content unit definition.
- Level grammar: verbs, objects, hazards, goals, constraints.
- Progression outline: introduction, variation, combination, mastery.
- Level table: id, goal, new idea, pressure, reward, difficulty, assets, data.
- Arcade wave table when relevant:
timeStart,duration,spawnLaneorxRange,fallSpeed,spawnInterval,hazardType,pickupType,telegraphMs,maxSimultaneous, andfairnessRule. - Encounter or wave spec: spawn order, timing, composition, and escalation.
- Procedural spec when relevant: seed policy, module pool, weighted picks, generation steps, validation rules, failover/fallback content, and difficulty budget.
- Fairness constraints: minimum escape gap, warning time, overlap rules, pickup-after-risk timing, and rest beats.
- Cocos data handoff: scene/prefab/table format and required components.
- Playtest questions: comprehension, difficulty, pacing, and replay value.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 83 lines · 79 tokens per session scan A b8db541b8913
cocos-level-content-design is a skill published in the GitHub repository lightblink/cocos-creator-local-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 955 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
cocos-asset-pipeline-director
Plan, generate, adapt, validate, and import Cocos Creator 3.x game assets through a configured Cocos Asset Forge-compatible MCP. Use whenever the user asks for Cocos assets, sprites, sprite sheets, tilesets, UI packs, effects, placeholders, audio, art bibles, Cocos-ready metadata, asset folders, bundle placement…
cocos-asset-review-director
Review generated or imported Cocos Creator game assets against game design, art direction, gameplay semantics, animation needs, technical quality, mobile readability, interaction feedback, audio fit, performance risk, and runtime import constraints. Use after asset generation or adaptation, before importing assets…
cocos-art-direction-director
Direct visual style, art bibles, asset consistency, prompt language, sprite readability, UI visual systems, animation style, and Cocos-ready asset QA for game art pipelines. Use before asset generation when Codex needs to define a coherent look, guide or critique generated assets, coordinate with cocosassetforge…
cocos-helper
A helper guide for building games with Cocos Creator, a game engine and editor. It covers project folders, common components, and managers written in TypeScript.
particle-modifier
A framework for creating and debugging custom particle modifiers in Cocos Creator 2.4.x, a tool for making games and interactive scenes. Particle modifiers can change properties such as position, color, size, rotation, and speed.
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.