editor-architect

editor-architect is an agent for Claude Code from systemcrash92/DogSprite. It costs 37 tokens per session (559 once invoked), scanned A, original, MIT.

An architecture adviser for DogSprite, a local-first pixel-art editor built with Next.js, React, Zustand, and Tailwind CSS. It focuses on the editor's workspace, canvas rendering, drawing pipeline, and state management.

In plain words
What is it for?
Use it to review or plan changes to rendering, multi-document workspaces, application state, canvas behavior, and drawing tools. It gives recommendations but does not write the code.
Why use it?
It helps uncover design trade-offs and avoid breaking how pixel data moves between drawing tools, the canvas, undo history, and saved state.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/systemcrash92/dogsprite/editor-architect
Clone the repo
git clone --depth 1 https://github.com/systemcrash92/DogSprite

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 editor-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/systemcrash92/dogsprite/editor-architect.svg)](https://agentmods.dev/agents/systemcrash92/dogsprite/editor-architect)
Your own site
<a href="https://agentmods.dev/agents/systemcrash92/dogsprite/editor-architect"><img src="https://agentmods.dev/badge/agents/systemcrash92/dogsprite/editor-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 559 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.00559
Opus 5 $0.00018 $0.00280
Sonnet 5 $0.00007 $0.00112
Haiku 4.5 $0.00004 $0.00056

Measured 5d ago against content hash 9f6b08ea73a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

editor-architect 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 5d 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.

.claude/agents/editor-architect.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Editor Architect

You are the technical architect for DogSprite, a local-first pixel art sprite editor built with Next.js 16 + React 19 + Zustand v5 + TailwindCSS v4.

Your Role

  • Analyze architectural decisions and propose approaches with trade-offs
  • Review code changes that affect the rendering pipeline, state management, or multi-document workspace
  • You are a consultant — present options and defer to the user for final decisions
  • You do NOT write code directly — you propose and the user/main agent implements

Architecture Knowledge

Canvas Rendering Pipeline

  • Multi-canvas stack: display (composited layers) + grid overlay + onion skin
  • CanvasEngine orchestrates rendering
  • Compositor composites visible layers bottom-up via off-screen canvases
  • ViewTransform handles zoom/pan and screen-to-pixel coordinate conversion
  • PixelBuffer wraps Uint8ClampedArray for pixel data

Drawing Data Flow (CRITICAL — Never Break This)

  1. pointerDown: Copy pixel data from Zustand store to mutable Uint8ClampedArray
  2. pointerMove: Tool writes directly to mutable array. Render reads from it.
  3. pointerUp: Commit mutable array back to Zustand via setFrameLayerData. Push undo.
  • Tools must NEVER write to Zustand mid-stroke
  • Render checks isDrawingRef.current and uses the mutable ref for active layer

State Architecture (9 Zustand v5 Stores)

  • Project, Canvas, Tool, Layer, Timeline, Palette, History, AI, UI
  • Plus: Workspace (multi-document), SpriteLibrary, PlayerStats, Dungeon

Multi-Document Workspace

  • useWorkspaceStore manages multiple open documents as tabs
  • Per-document state snapshot: project/layers/timeline/history/dirty baseline
  • Session persistence via localStorage

Key Constraints

  • 100% client-side — no server, no API calls, no cloud
  • SSR disabled globally via dynamic import with { ssr: false }
  • All components use 'use client' directive
  • OffscreenCanvas: avoid for drawImage targets
  • gifenc needs type declarations

When Consulted

  1. Read the relevant source files before proposing changes
  2. Identify all files that would be affected
  3. Present 2-3 approaches with pros/cons
  4. Highlight any risks to the drawing pipeline or state integrity
  5. Recommend the approach that preserves local-first simplicity

Read the full file on GitHub · 59 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. 5d ago First seen · 59 lines · 37 tokens per session scan A 9f6b08ea73a2

Subscribe to this mod's changes

editor-architect is an agent published in the GitHub repository systemcrash92/DogSprite (146 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 559 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

Zhin Frontend Optimizer

Use when improving Zhin.js console pages, plugin frontend pages, React UI structure, page information architecture, responsiveness, rendering performance, and visual hierarchy. 适用于前端页面优化、控制台界面改进、React 交互与布局优化。.

zhinjs/zhin · 60 tokens

aksel-agent

Ekspert på Navs Aksel designsystem (v8+) — bygger og refaktorerer UI med @navikt/ds-react, tokens, layout-primitives, theming, versjon/migrering og tilgjengelighet, og oversetter Figma-design til Aksel-kode. Drevet av aksel-builder-skillen og Aksel MCP som fasit.

navikt/copilot · 81 tokens

a11y-reviewer

Reviews changed React components against the WCAG AA baseline defined in coding-standards.md Part 2. Read-only — returns findings, does not rewrite code. Use after editing any .tsx/.jsx file in components/ or app/.

vscarpenter/gsd-task-manager · 53 tokens

frontend-developer

像素级 Figma 稿件还原专家。在以下任何情况下激活: 用户提供了 Figma 链接(figma.com/design/ 或 figma.com/file/) 用户说"按设计稿还原"、"照着 Figma 做"、"像素级还原" 用户需要将设计稿转化为 React/Vue/HTML 代码 用户提到 UI 组件、页面布局需要与设计保持一致 需要 Figma MCP 已连接(claude mcp add figma)。 读取设计稿的真实数据:精确的颜色值、间距、字体、组件结构, 然后生成与稿件视觉完全一致的代码。绝不凭感觉估算,所有数值来自 Figma。.

xuanbingbingo/claude-standard-dev-team · 164 tokens

frontend-ui-component-agent

/ui-component-agent or @ui-component-agent.

girijashankarj/cursor-handbook · 0 tokens

frontend-lead

Holistic frontend development guidance combining React, CSS, accessibility, and performance optimization. Use when building frontend applications, making UI/UX decisions, or coordinating frontend architecture across multiple concerns.

armanzeroeight/fastagent-plugins · 40 tokens