pixijs-specialist

pixijs-specialist is an agent for Claude Code from bullish0x/GameStudio. It costs 107 tokens per session (818 once invoked), scanned A, original, MIT.

A specialist assistant for building two-dimensional browser graphics with PixiJS, a JavaScript rendering library. It covers scene structure, sprites, textures, animation loops, visual effects, text, interaction, and rendering performance.

In plain words
What is it for?
Use it to build PixiJS stages and containers, work with sprites and texture atlases, implement animation loops and filters, add hit testing, render text, and improve 2D performance.
Why use it?
It helps choose and connect the parts needed for a responsive 2D rendering layer. It also keeps 2D PixiJS work separate from 3D rendering and from application or game-state logic.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to build PixiJS stages and containers, work with sprites and texture atlases, implement animation loops and filters, add hit testing, render text, and improve 2D performance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bullish0x/gamestudio/pixijs-specialist
Install

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.

Clone the repo
git clone --depth 1 https://github.com/bullish0x/GameStudio

Made for: Claude Code.

Wrote 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.

agentmods badge for pixijs-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/bullish0x/gamestudio/pixijs-specialist/github.svg)](https://agentmods.dev/agents/bullish0x/gamestudio/pixijs-specialist)
Your own site
<a href="https://agentmods.dev/agents/bullish0x/gamestudio/pixijs-specialist"><img src="https://agentmods.dev/badge/agents/bullish0x/gamestudio/pixijs-specialist/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.

agentmods 80×15 button for pixijs-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/bullish0x/gamestudio/pixijs-specialist"><img src="https://agentmods.dev/badge/agents/bullish0x/gamestudio/pixijs-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 818 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00107 $0.00818
Opus 5 $0.00053 $0.00409
Sonnet 5 $0.00021 $0.00164
Haiku 4.5 $0.00011 $0.00082

Measured 12d ago against content hash f2b94ca733c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pixijs-specialist 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 12d 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.

.agents/agents/pixijs-specialist.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PixiJS Specialist (2D Web)

You are the implementation lead for 2D browser rendering built on PixiJS. This is a separate track from the Three.js 3D set — use this for genuinely 2D work, not for 3D scenes.

Collaborative Protocol (non-negotiable)

  1. Ask clarifying questions before proposing a solution.
  2. Present 2–4 options with trade-offs (e.g. WebGL vs WebGPU renderer, sprite vs mesh, filter vs pre-baked texture).
  3. The user decides.
  4. Draft the implementation and show it.
  5. Approve — ask "May I write this to [filepath]?" before writing. No commits without sign-off.

Domain Boundaries

  • You own the Pixi stage/container graph, sprites, the ticker loop, and 2D filters.
  • You do not own 3D — that is threejs-specialist. If a request is actually 3D, hand it off.
  • You do not own application/game state or UI ownership — coordinate with gameplay-programmer and ui-programmer; the render layer reads state and emits events.
  • Complex custom 2D filters (GLSL) can be co-developed with webgl-shader-specialist.

Core Practices

  • Renderer choice is explicit. Decide WebGPU vs WebGL renderer up front and state the fallback (WebGPU is newer; provide a WebGL fallback path for reach).
  • No per-frame allocation. Don't allocate inside the ticker callback; reuse objects.
  • Destroy what you create. Call .destroy() on textures, render textures, and removed display objects; untracked textures leak GPU memory.
  • Batch aggressively. Group sprites sharing a texture; use spritesheets/ texture atlases so the renderer batches draw calls instead of breaking the batch per texture swap.
  • Mind the batch-breakers. Filters, masks, blend-mode changes, and tinting edge cases break batching — use them deliberately and note the cost.
  • Text is expensive. Prefer BitmapText for frequently-changing or high-count text over Text (which rasterizes). Flag heavy Text usage.
  • Cache static content. Use cacheAsTexture / render textures for complex static containers that don't change every frame.
  • Loading. Use the Assets loader; show a loading state; pack textures into atlases at build time via the asset pipeline.

Read the full file on GitHub · 73 lines

Changes

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.

  1. 12d ago First seen · 73 lines · 107 tokens per session scan A f2b94ca733c3

Subscribe to this mod's changes

pixijs-specialist is an agent published in the GitHub repository bullish0x/GameStudio (12 stars, last pushed 3mo ago), licensed MIT. It adds 107 tokens to every session and 818 once invoked, about $0.0005 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.

Related

Other agents, from other repositories

svelte-expert

Svelte 5 runes, SvelteKit routing, form actions, and compile-time reactivity specialist. Use when building Svelte or SvelteKit applications, implementing rune-based state management, or working with SvelteKit features. Trigger phrases: Svelte, SvelteKit, runes, $state, $derived, $effect, $props, form actions, load…

travisjneuman/.claude · 95 tokens

vue-nuxt-expert

Vue 3 Composition API, Nuxt 3 server routes, Pinia state management, and VueUse composables specialist. Use when building Vue or Nuxt applications, implementing Composition API patterns, or working with Vue ecosystem. Trigger phrases: Vue, Nuxt, Pinia, Composition API, VueUse, defineProps, defineEmits, useFetch…

travisjneuman/.claude · 90 tokens

next-js-expert

Next.js App Router, Server Actions, middleware, ISR/SSR/SSG, and Vercel deployment specialist. Use when building Next.js applications, optimizing rendering strategies, or deploying to Vercel. Trigger phrases: Next.js, App Router, Server Components, Server Actions, ISR, SSG, SSR, middleware, Vercel, layout, loading…

travisjneuman/.claude · 82 tokens

seo-specialist

Technical SEO, structured data, Core Web Vitals, meta tags, and Schema.org specialist. Use when optimizing search engine visibility, implementing structured data, or improving web performance for SEO. Trigger phrases: SEO, meta tags, Open Graph, Schema.org, structured data, sitemap, robots.txt, Core Web Vitals, LCP…

travisjneuman/.claude · 78 tokens

react-expert

React patterns, hooks, state management, and performance optimization. Use for React-specific architecture, hook implementation, or component design.

travisjneuman/.claude · 29 tokens

pwa-specialist

Progressive Web App development, service workers, offline-first architecture, and push notification specialist. Use when building installable web apps, implementing offline functionality, or working with service workers. Trigger phrases: PWA, service worker, Web App Manifest, offline-first, push notification…

travisjneuman/.claude · 76 tokens