Borrowing it
Nothing to install: this file belongs to isatimur/excalidraw-skill-pack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/isatimur/excalidraw-skill-pack/main/CLAUDE.mdgit clone --depth 1 https://github.com/isatimur/excalidraw-skill-packWrote 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/instructions/isatimur/excalidraw-skill-pack/claude-md)<a href="https://agentmods.dev/instructions/isatimur/excalidraw-skill-pack/claude-md"><img src="https://agentmods.dev/badge/instructions/isatimur/excalidraw-skill-pack/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.
<a href="https://agentmods.dev/instructions/isatimur/excalidraw-skill-pack/claude-md"><img src="https://agentmods.dev/badge/instructions/isatimur/excalidraw-skill-pack/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01981 | $0.01981 |
| Opus 5 | $0.00991 | $0.00991 |
| Sonnet 5 | $0.00396 | $0.00396 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
excalidraw-skill-pack 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 94 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.
What this is
A skill pack that makes AI agents produce good Excalidraw diagrams — visual arguments, not labeled boxes. The product is the methodology (packages/core/SKILL.md) plus themes and a dual-language renderer. The shipped artifacts are npm + PyPI packages and per-agent install adapters; there is no long-running application.
Commands
pnpm workspace (Node ≥20, pnpm 8.9.2). Run from repo root unless noted.
pnpm install
pnpm build # tsc across all packages (pnpm -r build)
pnpm test # vitest across all packages
pnpm lint # eslint
pnpm typecheck # tsc --noEmit
pnpm exec playwright install chromium # required before renderer tests run
- Single package:
pnpm --filter @excalidraw-skill-pack/core test(orbuild/lint/typecheck). - Single test file:
pnpm --filter @excalidraw-skill-pack/render exec vitest run tests/parity.test.ts. - Watch one file: append the path to
vitestwithoutrun.
Python renderer (packages/renderer-python/, uses uv, requires Python ≥3.11):
cd packages/renderer-python
uv sync && uv run playwright install chromium
uv run pytest # all
uv run pytest tests/test_canary.py # single
uv run ruff check && uv run ruff format && uv run mypy --strict
Architecture
Monorepo layout (packages/)
core/(@excalidraw-skill-pack/core) — the methodology.SKILL.mdis the prompt agents actually read;theme.schema.json+validate-theme.tsvalidate theme JSON (Ajv);theme-loader.tsdiscovers and resolves themes. Bundles thedefault-sketchytheme. Has thevalidate-themebin. Every other package depends on this.renderer-node/(@excalidraw-skill-pack/render) — renders.excalidrawJSON → PNG by loadingsrc/render_template.htmlin headless Chromium via Playwright. Exposes theexcalidraw-renderCLI (commander).renderer-python/(excalidraw-skill-pack-render) — a parity mirror of the Node renderer. It ships the samerender_template.html; both renderers must produce pixel-identical output (see Visual regression below).mcp-server/(@excalidraw-skill-pack/mcp-server) — stdio MCP server. Each tool is one file insrc/tools/:generate_diagram_prompt,render_diagram,apply_theme,list_themes,audit_diagram.server.tsis a thin dispatcher over a tool registry.themes/<name>/— published, curated themes (dark,notion,stripe-press,whiteboard). Each is a dual npm + PyPI package:package.json+pyproject.toml,theme.json(manifest),palette.{json,md},typography.json, andelements/+layouts/markdown that gets spliced into agent prompts.create-excalidraw-theme/(@excalidraw-skill-pack/create-theme) — Mustache scaffolder for new theme packages (src/template/).install/(@excalidraw-skill-pack/install) — meta-installer. Its build copiesadapters/intodist/adapters/;ADAPTERSinsrc/index.tsis the source of truth for supported agents.shared/fixtures/— canonical.excalidrawexample diagrams +golden/baseline images used by renderer tests.
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.
- 8d ago First seen · 94 lines · 1,981 tokens per session scan A 0f7dc5cabb17
excalidraw-skill-pack CLAUDE.md is an instructions file published in the GitHub repository isatimur/excalidraw-skill-pack (4 stars, last pushed today), licensed MIT. It adds 1,981 tokens to every session, about $0.0099 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.
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.
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.
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).
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).
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.
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.