What is plano CLAUDE.md?

Development instructions for PLANO, an Electron desktop app with an infinite canvas for arranging terminals, editors, browsers, files, notes, and AI agents. Its terminals can detect when a coding agent is running.

Use them to install dependencies, run the app, rebuild native terminal components, build releases, and type-check both the desktop and web code.

They document the project structure, required design references, setup commands, and platform-specific environment problems.

How zqkra/plano configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to zqkra/plano. 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/zqkra/plano/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/zqkra/plano

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zqkra/plano/claude-md.svg)](https://agentmods.dev/instructions/zqkra/plano/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/zqkra/plano/claude-md"><img src="https://agentmods.dev/badge/instructions/zqkra/plano/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 4,552 This file is loaded in full into every session.

When invoked 4,552 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.

Model	Per session	Once invoked
Fable 5.1	$0.04552	$0.04552
Opus 5	$0.02276	$0.02276
Sonnet 5	$0.00910	$0.00910
Haiku 4.5	$0.00455	$0.00455

Measured 6d ago against content hash 36a83e057406, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

plano 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.

CLAUDE.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 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 PLANO is

A desktop app (Electron): an infinite-canvas workspace IDE. One spatial pan/zoom canvas per project where the user drops floating panels — terminals, code editors, browsers, AI agents, file explorer, git, markdown, sticky notes, text, regions. Layout persists per project. Signature feature: terminals auto-detect when an AI coding CLI (Claude Code, Codex, …) is running inside them and morph into "agent mode".

Full specs live in docs/architecture/ARCHITECTURE.md and docs/design/DESIGN_SYSTEM.md — read them before non-trivial changes. Use docs/README.md as the documentation index.

Commands

npm install            # deps (see Electron-binary gotcha below)
npm run rebuild        # rebuild node-pty against Electron's ABI (needs VS C++ Build Tools on Windows)
npm run dev            # launch with HMR (renderer) + hot-reload (main/preload)
npm run build          # electron-vite production build into out/
npm run typecheck      # tsc --noEmit for BOTH projects (node + web); run before considering work done
npm run typecheck:node # main + preload + shared only
npm run typecheck:web  # renderer + shared only
npm run dist           # build + package an installer (electron-builder)

There is no test runner wired yet and no linter configured (ESLint is referenced in comments but not installed). npm run typecheck is the only automated gate — always run it after edits.

Environment gotchas (Windows — hit these during setup)

Electron binary may be missing after npm install. Symptom: npm run dev fails with Error: Electron uninstall. Cause: a corrupt zip in %LOCALAPPDATA%\electron\Cache makes @electron/get report a false "cache hit", and Electron's own extract-zip silently stops after the first file. Fix: extract the cached zip manually — Expand-Archive <cache>\electron-v*-win32-x64.zip node_modules/electron/dist -Force then write electron.exe into node_modules/electron/path.txt.
node-pty is native. npm run rebuild (electron-rebuild) needs the Visual Studio "Desktop development with C++" workload. If it's absent, terminals can't be built from source. In practice the prebuilt node-pty binary for Node 20 has matched Electron 33's ABI, so terminals load without a rebuild — but don't rely on it across Electron upgrades.
node-pty loads tolerantly: PtyManager lazy-requires node-pty and, on failure, streams a guidance message to the terminal panel instead of crashing the app. Keep that resilience when touching PtyManager.
Known open issue: under Electron on Windows, node-pty's conpty_console_list_agent can throw AttachConsole failed. This is a ConPTY-console-list problem, not an ABI problem. Wrap mod.spawn(...) defensively when working in PtyManager.

Read the full file on GitHub · 110 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.

6d ago First seen · 110 lines · 4,552 tokens per session scan A 36a83e057406

Subscribe to this mod's changes

plano CLAUDE.md is an instructions file published in the GitHub repository zqkra/plano (5 stars, last pushed 6d ago), licensed MIT. It adds 4,552 tokens to every session, about $0.0228 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.

ai-agents desktop-app developer-tools electron infinite-canvas

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 · 5,182 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

plano: Instructions file for Claude Code