What is scratch-tabs CLAUDE.md?

A project guide for Scratch Tabs, a local-first web app for exploring and transforming text and data formats. It describes the React, TypeScript, Vite, Zustand, Monaco, and IndexedDB setup.

Use it to work on the interface, state stores, services, format detectors, utility tools, builds, tests, linting, type checks, or browser tests.

It gives coding agents the project map, standard commands, and architecture rules needed to make changes consistently.

How spectra-g/scratch-tabs configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to spectra-g/scratch-tabs. 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/spectra-g/scratch-tabs/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/spectra-g/scratch-tabs

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/spectra-g/scratch-tabs/claude-md.svg)](https://agentmods.dev/instructions/spectra-g/scratch-tabs/claude-md)

Your own site

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

Per session 1,194 This file is loaded in full into every session.

When invoked 1,194 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	$0.01194	$0.01194
Opus 5	$0.00597	$0.00597
Sonnet 5	$0.00239	$0.00239
Haiku 4.5	$0.00119	$0.00119

Measured 6d ago against content hash d837eac62bb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

scratch-tabs 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 · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 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

App: Scratch Tabs — local-first developer workspace for exploring and transforming text/data formats
Type: React + TypeScript SPA
Build tool: Vite
State: Zustand
Editor: Monaco
Storage: IndexedDB (via Dexie)

Core Commands

npm install
npm run dev          # starts on http://localhost:5173
npm run build
npm run lint
npm run tsc
npm run test
npm run test:watch
npm run coverage
npm run e2e          # excludes @wip/@bug tags; auto-starts dev server
npm run e2e:full     # all tags; use this when running a specific feature file

Run a single feature file:

npm run e2e:full -- tests/e2e/features/undo.feature

Run by tag:

npm run e2e:full -- --tags @wip

Changelog generation:

cd changelog && npm run generate

Code Map

src/components/: UI and page composition
src/stores/: Zustand stores and root actions
src/services/: business logic and integrations
src/formats/: format detectors and smart views (self-registering)
src/tablets/: standalone utility tools (self-registering)
src/features/: feature-flag-gated functionality
src/views/: full-page view components
src/hooks/: shared React hooks
src/workers/: Web Workers for heavy computation
src/db/: storage layer (Dexie/IndexedDB schema)
tests/e2e/: Playwright/Cucumber tests
landing/: static marketing pages

Architecture Guardrails

Monaco model is the live content source.
- Use src/services/modelManager.ts for model lifecycle/content reads.
Zustand tab content is the last-known/saved state.
- Keep store updates consistent with model changes.
Do not add cursor-position React state.
- Cursor/view state belongs to Monaco and persisted storage paths.
Keep inactive workspace content out of active in-memory flows.
- For cross-workspace views, prefer metadata-only reads unless full content is required.

Read the full file on GitHub · 138 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 · 138 lines · 1,194 tokens per session scan A d837eac62bb6

Subscribe to this mod's changes

scratch-tabs CLAUDE.md is an instructions file published in the GitHub repository spectra-g/scratch-tabs (5 stars, last pushed 2d ago), licensed MIT. It adds 1,194 tokens to every session, about $0.0060 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.

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

scratch-tabs: Instructions file for Claude Code