agentmods.dev

sketch-spark-diagrams: Instructions file for Claude Code

CLAUDE.md

sketch-spark-diagrams CLAUDE.md is an instructions file for Claude Code from kaushalsahu07/sketch-spark-diagrams. It costs 544 tokens per session, scanned A, original, MIT.

Development instructions for SketchSpark, a collaborative online whiteboard that uses AI to create diagrams. They describe its React and TypeScript app, canvas, AI features, and architecture.

In plain words
What is it for?
They help with work on the whiteboard, diagram generation, canvas editing, AI chat, and automatic saving.
Why use it?
They give a coding agent the project context needed to make changes that fit the existing application.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is kaushalsahu07/sketch-spark-diagrams's own configuration. It tells Claude Code how to work on sketch-spark-diagrams itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sketch-spark-diagrams configures →

not rated 5repo 3mo ago A scan 544 tokens original MIT
View source ↗ kaushalsahu07/sketch-spark-diagrams sketchspark.netlify.app
Reuse

Borrowing it

Nothing to install: this file belongs to kaushalsahu07/sketch-spark-diagrams. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kaushalsahu07/sketch-spark-diagrams/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kaushalsahu07/sketch-spark-diagrams

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 sketch-spark-diagrams CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kaushalsahu07/sketch-spark-diagrams/claude-md/github.svg)](https://agentmods.dev/instructions/kaushalsahu07/sketch-spark-diagrams/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kaushalsahu07/sketch-spark-diagrams/claude-md"><img src="https://agentmods.dev/badge/instructions/kaushalsahu07/sketch-spark-diagrams/claude-md/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 sketch-spark-diagrams CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kaushalsahu07/sketch-spark-diagrams/claude-md"><img src="https://agentmods.dev/badge/instructions/kaushalsahu07/sketch-spark-diagrams/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 544 This file is loaded in full into every session.
When invoked 544 The same file — it is already loaded in full.
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 $0.00544 $0.00544
Opus 5 $0.00272 $0.00272
Sonnet 5 $0.00109 $0.00109
Haiku 4.5 $0.00054 $0.00054

Measured 11d ago against content hash 2c0ba8ba998f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sketch-spark-diagrams CLAUDE.md 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 11d 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.md · 32 lines

What it actually says

SketchSpark - AI-Powered Whiteboard

SketchSpark is a collaborative whiteboard application that leverages AI to help users create and generate diagrams effortlessly.

Tech Stack

  • Frontend: React, TypeScript, Vite
  • Styling: Tailwind CSS, shadcn-ui
  • Canvas Engine: Fabric.js
  • AI Integration:
    • Google Gemini (via src/lib/graphviz.ts & src/lib/mistral.ts) for diagram generation (Fabric.js JSON).
    • Cohere (via src/lib/cohere.ts) for canvas-aware chat.

Core Architecture

  • src/components/Canvas.tsx: The heart of the application. Manages the Fabric.js canvas, drawing tools, keyboard shortcuts, and auto-save to localStorage.
  • src/components/AIAssistant.tsx: Interface for AI interactions.
    • Generate Mode: Prompts Gemini to produce a JSON structure of Fabric.js objects.
    • Chat Mode: Sends canvas description and user prompt to Cohere for textual assistance.
  • src/components/DiagramPreview.tsx: Allows users to review and potentially modify AI-generated diagrams before adding them to the canvas.
  • src/lib/graphviz.ts: Low-level integration with Google Gemini API.
  • src/lib/mistral.ts: High-level logic for prompting Gemini to generate diagram JSON.
  • src/lib/cohere.ts: Integration with Cohere Chat API.

Key Concepts

  • Fabric.js JSON: The AI generates diagrams as JSON arrays of objects (rect, circle, text, line, path) which are then loaded into the Fabric.js canvas.
  • Canvas Description: The AI Assistant provides a summary of the current canvas objects (e.g., "Canvas contains: 2 rects, 1 circle") to provide context to the LLMs.
  • Theme Awareness: The application supports light and dark modes, and the AI is instructed to use light colors (like white) for text when the background is dark.

Development Guidelines

  • Drawing Tools: New shapes should be added to the Tool type in Canvas.tsx and handled in createShape and handleMouseDown/MouseMove/MouseUp.
  • AI Prompting: Diagram generation prompts are located in src/lib/mistral.ts. Ensure the output format strictly follows the Fabric.js JSON structure.
  • Styling: Use Tailwind CSS and shadcn-ui components.
  • Canvas State: Canvas data is saved to localStorage under the key canvasData.
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. 11d ago First seen · 32 lines · 544 tokens per session scan A 2c0ba8ba998f

Subscribe to this mod's changes

sketch-spark-diagrams CLAUDE.md is an instructions file published in the GitHub repository kaushalsahu07/sketch-spark-diagrams (5 stars, last pushed 3mo ago), licensed MIT. It adds 544 tokens to every session, about $0.0027 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.

aiai-poweredcodelovablereactjswhiteboard
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens