chartpane CLAUDE.md

chartpane CLAUDE.md is an instructions file for coding agents from ahmadsl/chartpane. It costs 2,443 tokens per session, scanned A, original, MIT.

A repository instruction file that tells Claude Code how this Chart.js chart app is built, tested, and organized. Chart.js is a JavaScript library for drawing charts.

In plain words
What is it for?
It helps with building, deploying, running the development server, and running all tests, one test file, or tests matching a name.
Why use it?
It gives the agent the project's commands, architecture, and testing patterns, reducing incorrect changes and unnecessary exploration.

Instructions file

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 instructions/ahmadsl/chartpane/claude-md
Clone the repo
git clone --depth 1 https://github.com/ahmadsl/chartpane

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 chartpane CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ahmadsl/chartpane/claude-md.svg)](https://agentmods.dev/instructions/ahmadsl/chartpane/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ahmadsl/chartpane/claude-md"><img src="https://agentmods.dev/badge/instructions/ahmadsl/chartpane/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,443 This file is loaded in full into every session.
When invoked 2,443 The same file — it is already loaded in full.
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 $0.02443 $0.02443
Opus 5 $0.01222 $0.01222
Sonnet 5 $0.00489 $0.00489
Haiku 4.5 $0.00244 $0.00244

Measured 4d ago against content hash 87747604db76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chartpane 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 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.

CLAUDE.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

npm run build          # Type-check (tsc --noEmit) + bundle UI into dist/mcp-app.html
npm start              # wrangler dev + vite build --watch (port 8787)
npm run dev            # wrangler dev + sandbox dev server (localhost:3456)
npm run deploy         # Deploy to Cloudflare Workers
npm test               # Run all tests (vitest)
npm run test:watch     # Run tests in watch mode

# Run a single test file
npx vitest run tests/unit/config.test.ts

# Run tests matching a name pattern
npx vitest run -t "scatter"

Architecture

MCP App that renders Chart.js charts inline in Claude's UI. Two tools: render_chart (single chart) and render_dashboard (multi-chart grid).

Data Flow

Claude tool call → server.ts (validate, pass through ChartInput as structuredContent)
    → mcp-app.ts (ontoolresult) → buildChartConfig() → Chart.js renders to canvas

The server is intentionally thin — it validates input and returns the raw ChartInput as structuredContent. All Chart.js config transformation happens browser-side in shared/config.ts.

Module Layout

  • server.ts — MCP server factory: createServer(options: ServerOptions) with htmlLoader and onLog params. Platform-agnostic (no fs/path/url). Tool registration via registerAppTool/registerAppResource.
  • worker.ts — Cloudflare Workers entry point: createMcpHandler from agents/mcp with apiRoute: "/mcp", ASSETS binding for static HTML, DB binding for D1 request logging, and normalizeResourceParam() workaround for OAuthProvider audience bug.
  • auth-handler.ts — Hono app with /authorize (GET/POST) and /callback routes for Google OAuth via @cloudflare/workers-oauth-provider. Uses workers-oauth-utils.ts for CSRF, state management, consent dialog.
  • workers-oauth-utils.ts — OAuth utilities: CSRF protection, KV-backed state, cookie signing, consent dialog HTML. Workers-only (uses crypto.subtle.timingSafeEqual).
  • src/mcp-app.ts — Browser-side UI: App from @modelcontextprotocol/ext-apps, ontoolresult/ontoolinput/onhostcontextchanged handlers, Chart.js rendering.
  • shared/ — Pure modules imported by both server and UI:
    • types.ts — Zod schemas (ChartInput, DashboardInput, RenderResult)
    • validation.ts — Schema parsing + business rules (scatter needs {x,y}, pie max 1 dataset, etc.)
    • config.tsbuildChartConfig() transforms ChartInput → Chart.js ChartConfiguration
    • colors.ts — 12-color palette; per-slice for pie/doughnut, per-dataset for others
    • grid.tscalculateColumns() for dashboard layout

Read the full file on GitHub · 112 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. 4d ago First seen · 112 lines · 2,443 tokens per session scan A 87747604db76

Subscribe to this mod's changes

chartpane CLAUDE.md is an instructions file published in the GitHub repository ahmadsl/chartpane (1 stars, last pushed 6mo ago), licensed MIT. It adds 2,443 tokens to every session, about $0.0122 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 instructions, from other repositories

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

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 · 5,182 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 · 4,345 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

next.js 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