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/playcanvas/skills/add-effectsnpx skills add playcanvas/skills --skill add-effectsgit clone --depth 1 https://github.com/playcanvas/skillsWrote 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/playcanvas/skills/add-effects)<a href="https://agentmods.dev/skills/playcanvas/skills/add-effects"><img src="https://agentmods.dev/badge/skills/playcanvas/skills/add-effects.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 5.1 | $0.00039 | $0.01274 |
| Opus 5 | $0.00019 | $0.00637 |
| Sonnet 5 | $0.00008 | $0.00255 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
add-effects 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 yesterday.
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.
This is a copy
100% identical to add-effects — 23 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Effects and game feel
Trigger transient effects through application events and reuse their resources.
Reuse before authoring. Adapt the closest official particle example with find-examples, prefer the
Engine's built-in particle component over a hand-written system, and discover any shipped trail or
effect script with reuse-scripts.
Copy particle curve construction from the installed example exactly. CurveSet takes one key array
per channel, such as new CurveSet([0, x0, 1, x1], [0, y0, 1, y1], [0, z0, 1, z1]); do not flatten three channels into one array. A malformed curve can type-check and then fail
inside the particle texture upload. Create one emitter, render a frame, and require empty runtime
and console diagnostics before reusing the helper for smoke, spray, or splashes.
For a polished wake, smoke, or spray requirement, do not stop at scaled planes, crossed billboards, or generic render primitives. Use the built-in particle component for smoke and spray; reserve a custom mesh and material for a continuously sampled wake ribbon. Verify tint and blending against the actual scene lighting and surface.
Place and layer
- Place an effect at the emitter's world mount point; parent it there or copy the world transform once.
- Keep additive or transparent effects above the surface they sit on and biased toward the camera so they do not z-fight. Inspect soft transparency at grazing angles for hard edges, black quads, or dropout.
- Size and orient effects from the emitter's calibrated bounds, not a guessed constant.
Pool and prewarm
- Create emitters, ribbons, flashes, materials, and meshes at load. Events check out an effect, set
its transform, and call
particlesystem.reset()thenplay(); after its particles finish, callstop()and return it to the pool. - First-use shader compilation can stall a frame. Before gameplay, render every material and particle variant through the relevant passes, on an offscreen rig or behind the ready overlay.
- Pulse or tint uniforms with
meshInstance.setParameterormaterial.setParameter.material.update()marks the whole material dirty and clears variants when defines or chunks change; reserve it for material changes that require it.
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.
- yesterday Changed · +11 lines 2c0a2b55830b
- 6d ago First seen · 82 lines · 39 tokens per session scan A 8f76d8bcbfe1
add-effects is a skill published in the GitHub repository playcanvas/skills (14 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,274 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to add-effects, differing in 23 lines, and is treated as a copy.
Other skills, from other repositories
html-ppt-zhangzara-8-bit-orbit
A gamer's journey building a retro-arcade collection — the obsession, the hunt, and what the machines came to mean. Built as a decision-grade story deck for friends, hobby community.
worker-visualizer
A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas at 60fps. Produced as a single self-contained index.html. Use when the brief asks for a "web worker", "simulation"…
game-skill-orchestration
Coordinate multiple game-development skills and produce outcome-first briefs, plans, reviews, and validation flows. Use when Codex is asked to explore the game skillset, route a broad game project across disciplines, improve skill quality, plan a full game feature, combine…
game-3d-development
Plan, implement, debug, and review real-time 3D game development work. Use when Codex is asked to build or improve 3D gameplay, cameras, controllers, physics interactions, animation integration, spatial UI, scene architecture, composition/component architecture, performance, rendering, Three.js, Unity, Unreal, Godot…
game-cinematic-cutscene-design
Design, storyboard, implement, render, and review game cutscenes, intro videos, cinematics, trailers, and in-engine camera sequences. Use when Codex is asked about storyboards, animatics, shot lists, blocking, camera language, Sequencer, Unity Timeline, Cinemachine, Unreal cinematics, Blender storyboarding, intro…
game-multiplayer-design
Design, implement, debug, and review multiplayer game systems. Use when Codex is asked about client/server architecture, authoritative servers, listen servers, dedicated servers, peer-to-peer, replication, prediction, interpolation, rollback, lag compensation, matchmaking, lobbies, sessions, state synchronization…