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 agentmods add skills/andvolodko/html5-game-editor/add-node-typenpx skills add andvolodko/html5-game-editor --skill add-node-typegit clone --depth 1 https://github.com/andvolodko/html5-game-editorWrote 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/andvolodko/html5-game-editor/add-node-type)<a href="https://agentmods.dev/skills/andvolodko/html5-game-editor/add-node-type"><img src="https://agentmods.dev/badge/skills/andvolodko/html5-game-editor/add-node-type.svg" alt="Measured on agentmods" 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 | $0.00077 | $0.02172 |
| Opus 5 | $0.00039 | $0.01086 |
| Sonnet 5 | $0.00015 | $0.00434 |
| Haiku 4.5 | $0.00008 | $0.00217 |
Grade A, and why
add-node-type 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 4d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Node Type
Canonical workflow for a new scene node type (component composition, not a JS class hierarchy). Do not invent a parallel node-type inheritance tree.
Script behaviours (defineComponent) are not node types — use .cursor/skills/create-game-component/SKILL.md.
Persisted format changes: also follow .cursor/skills/modify-scene-schema/SKILL.md.
When to use this skill
- Adding a creatable type to Hierarchy / Toolbar Node menu (
pixi.*/three.*ids). - Adding a new leaf visual (
Sprite-like) or leaf Three component (Model3D-like). - Adding an extra on Transform2D nodes (pattern: Hit Zone, Mask — not leaves).
- A type exists in schema but menus, Inspector, renderer, or clone/undo are incomplete.
Before changing code
- Search for the closest existing type and copy that vertical slice. Do not design a new registration style.
- Classify the type:
| Kind | Domain | Registry id | Children |
|---|---|---|---|
| 2D leaf visual | packages/scene/src/visual-components.ts |
pixi.<kebab> |
no |
| 2D container | Transform2D only | pixi.container |
yes |
| Extra on 2D node | hit-zone-component.ts / mask-component.ts |
pixi.hit-zone / pixi.mask |
Hit Zone/Mask nodes yes; adding onto a leaf does not change leaf parenting |
| 3D leaf | packages/scene/src/three-components.ts |
three.<kebab> |
no |
| 3D container | Transform3D only | three.container |
yes |
- Confirm it is not a Script (
type: "Script"). Scripts reusecreateScriptComponent. - Read
docs/scene-model.md(How to extend) anddocs/renderers.md. Follow.cursor/rules/architecture.mdcand.cursor/rules/class-size.mdc(keep visual-components → schema → factories → node-types → painters → Inspector aligned, one category per file).
Never ship a partial type. Schema without renderer, menu, Inspector, clone, or tests is incomplete.
Implementation workflow
Copy this checklist and complete it in order. Skip a layer only when the closest existing type also skips it (and document why).
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.
- 4d ago First seen · 131 lines · 77 tokens per session scan A 056f1444e9de
add-node-type is a skill published in the GitHub repository andvolodko/html5-game-editor (6 stars, last pushed 9d ago), licensed MIT. It adds 77 tokens to every session and 2,172 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
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…