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.
npx agentmods add instructions/whq25/agent-canvas/claude-mdgit clone --depth 1 https://github.com/WHQ25/agent-canvasWrote 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/whq25/agent-canvas/claude-md)<a href="https://agentmods.dev/instructions/whq25/agent-canvas/claude-md"><img src="https://agentmods.dev/badge/instructions/whq25/agent-canvas/claude-md.svg" alt="Measured on agentmods" 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 | $0.02152 | $0.02152 |
| Opus 5 | $0.01076 | $0.01076 |
| Sonnet 5 | $0.00430 | $0.00430 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
agent-canvas 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 6d 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 — 204 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.
Project Overview
Agent Canvas is an AI agent skill + CLI tool that provides an Excalidraw canvas interface for AI agents. It consists of:
- skills/agent-canvas/: Agent skill (teaches AI agents how to use the CLI)
- packages/: NPM packages in a Turborepo monorepo
- web-app: Browser frontend with Excalidraw
- cli: Command-line interface with built-in HTTP/WebSocket server
Tech Stack
- Package Manager: Bun
- Monorepo: Turborepo
- Web App: Vite + React + @excalidraw/excalidraw (0.18.0)
- CLI: Commander.js + ws (WebSocket client)
- Language: TypeScript
Development Commands
# Install dependencies (from root)
bun install
# Start dev server (Vite HMR + WS relay, auto-opens browser)
bun run dev
# Run CLI commands during development (use this instead of global `agent-canvas`)
bun dev:cli <command>
# Example: bun dev:cli add-shape -t rectangle -x 100 -y 100
# Build all packages
bun run build
# Type check
bun run typecheck
Important: When developing, always use bun dev:cli instead of the globally installed agent-canvas command. The global version is the published release and won't include your local changes.
Dev Mode (start --dev)
bun run dev (or bun dev:cli start --dev) starts a development server with Vite HMR:
- WS relay on port 7900 (dev default, overridable via
AGENT_CANVAS_WS_PORT) - Vite dev server on port 5173 (Vite default) with hot module replacement
- No
bun run buildneeded — web-app changes auto-reload in browser
| WS Port | HTTP Port | |
|---|---|---|
Production (start) |
7890 | 7891 |
Dev (start --dev) |
7900 | 5173 (Vite) |
Workflow:
- Run
bun run devto start dev server (Vite HMR + WS relay) - Make code changes in
packages/web-app/src/— browser auto-reloads - For CLI changes in
packages/cli/src/, restart the dev server - Test CLI commands with
bun dev:cli <command>
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.
- 6d ago First seen · 204 lines · 2,152 tokens per session scan A 87ab954493d3
agent-canvas CLAUDE.md is an instructions file published in the GitHub repository WHQ25/agent-canvas (33 stars, last pushed 6mo ago), licensed MIT. It adds 2,152 tokens to every session, about $0.0108 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.
Other instructions, from other repositories
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
slivingdoc AGENTS.md
AGENTS.md instructions for baalimago/slivingdoc, covering agents.md — slivingdoc, architecture, package map, event flow and startup wiring (main.go).