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/merijjeyn/drawpad/agents-mdgit clone --depth 1 https://github.com/merijjeyn/drawpadWrote 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/merijjeyn/drawpad/agents-md)<a href="https://agentmods.dev/instructions/merijjeyn/drawpad/agents-md"><img src="https://agentmods.dev/badge/instructions/merijjeyn/drawpad/agents-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 | $0.01242 | $0.01242 |
| Opus 5 | $0.00621 | $0.00621 |
| Sonnet 5 | $0.00248 | $0.00248 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
drawpad AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — guidance for AI agents working in this repo
What this project is
drawpad is a Go CLI that opens a small Chrome window with an Excalidraw
canvas so an AI agent and a human can collaborate on a diagram. The
drawpad binary is on PATH — invoke it directly as drawpad, never as
bin/drawpad or an absolute path. See drawpad --help for the user-facing
contract (it is written for both humans and agents — read it before
invoking the tool).
Use drawpad to talk back to the user when a picture beats text
This repo ships a tool whose entire purpose is visual communication with the
user. When you are operating in this repo (or anywhere drawpad is on
PATH), reach for it whenever a diagram would land faster than prose.
Concrete triggers:
- Architecture showcases. Before writing or refactoring multi-component
code, sketch the layering / module graph in
drawpadand ask the user to confirm or red-line it. Cheaper than writing the wrong code. - Design decisions with tradeoffs. When two or three structural options exist, draw them side by side and let the user point at the one they want (or annotate "no, like this").
- Flows, sequences, state machines. Boxes and arrows convey ordering better than numbered lists.
- UI / UX proposals. Wireframe the page in
drawpadinstead of describing it. The user will fix proportions and labels with one mouse drag. - Asking the user to sketch their idea. Hand them a blank canvas with
--prompt "draw what you want". Their scribble + one-line comment will unstick you faster than three rounds of clarifying questions.
Don't use drawpad for trivial confirmations, things that fit in one line
of text, or when no display is available (e.g. CI, headless SSH).
How to invoke it
drawpad \
--prompt "Question shown above the canvas." \
--initial scene.json \ # optional; omit for a blank canvas
--output result.json \ # or omit / "-" for stdout
--screenshot-dir ./screenshots
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.
- 4d ago First seen · 115 lines · 1,242 tokens per session scan A e8a52c9a7874
drawpad AGENTS.md is an instructions file published in the GitHub repository merijjeyn/drawpad (18 stars, last pushed 3mo ago), licensed MIT. It adds 1,242 tokens to every session, about $0.0062 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
solidworks-api-skill CLAUDE.md
Instructions for guoleizhen717/solidworks-api-skill, covering solidworks api skill repository, repository purpose, skill scope and project conventions.
q3ds-solidworks-mcp AGENTS.md
AGENTS.md instructions for zarcherlot/q3ds-solidworks-mcp, covering codex repository guidance, architecture, drawing planning and verification.
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).
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.
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.
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.