What is claude-design-premium CLAUDE.md?

A setup and operating guide for Claude Design Web, a browser-based design environment. It explains the project’s document-backed workflow and how its reusable instruction files are applied.

Use it when setting up the design workspace, running its canvas script process, or following the project’s activation and setup procedures.

It tells the agent when setup is required and what must happen before handling a new request. This helps prevent work from starting with an unconfigured design environment.

How oalanicolas/claude-design-premium configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to oalanicolas/claude-design-premium. 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/oalanicolas/claude-design-premium/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/oalanicolas/claude-design-premium

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/oalanicolas/claude-design-premium/claude-md/github.svg)](https://agentmods.dev/instructions/oalanicolas/claude-design-premium/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/oalanicolas/claude-design-premium/claude-md"><img src="https://agentmods.dev/badge/instructions/oalanicolas/claude-design-premium/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/oalanicolas/claude-design-premium/claude-md"><img src="https://agentmods.dev/badge/instructions/oalanicolas/claude-design-premium/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,873 This file is loaded in full into every session.

When invoked 5,873 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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	$0.05873	$0.05873
Opus 5	$0.02936	$0.02936
Sonnet 5	$0.01175	$0.01175
Haiku 4.5	$0.00587	$0.00587

Measured 9d ago against content hash 3ed0543a292f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-design-premium 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 9d 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 · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Design Premium Protocol

You operate inside Claude Design Web under a document-backed premium UI protocol.

Runtime contract: docs/canvas-runtime.md · Script pipeline: docs/script-pipeline.md · Honest limits: LIMITATIONS.md

Claude Design Web has a fixed, closed set of native product Skills. This starter does not install new native Skills. Instead, this root CLAUDE.md acts as the bootstrap file, and the .skill.md files are documental procedures: reusable operating instructions that you apply when relevant. Apply only the procedures relevant to the current task - except harness-auto-setup, which always runs first when the harness is unconfigured (see below).

Auto-bootstrap gate (HIGHEST PRIORITY - runs before everything)

On every new conversation, before interpreting the user's message, check whether the harness needs setup. If yes, run scripts/context-signals.mjs logic, then skills/harness-auto-setup.skill.md immediately and completely - do not ask permission, do not wait for a magic keyword. Execute the script pipeline in docs/script-pipeline.md, not a hand-waved summary.

Setup needed when ANY of these is true

styles.css contains UNBOUND
BOUND_DS.json is missing or has no namespace
DESIGN.md contains CDP:UNCONFIGURED or §1 template filler (Describe the product's visual register)
Any root *.dc.html contains {{DS_HELMET_BLOCK}} or {{BOUND_DS_
BOUND_DS.json is stale or out of sync with the live DS (bindingSchemaStale / bindingOutOfSync in context-signals)

Setup complete when ALL of these pass

BOUND_DS.json exists with hostMode, bindingSource, namespace, root, components, globalCssPaths and matches live DS detection
DESIGN.md names the real product/DS and has no stub phrases
styles.css re-exports the bound DS (@import lines, no UNBOUND)
All *.dc.html helmets are patched (zero {{ placeholders)

Read the full file on GitHub · 366 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.

9d ago First seen · 366 lines · 5,873 tokens per session scan A 3ed0543a292f

Subscribe to this mod's changes

claude-design-premium CLAUDE.md is an instructions file published in the GitHub repository oalanicolas/claude-design-premium (268 stars, last pushed 2mo ago), licensed MIT. It adds 5,873 tokens to every session, about $0.0294 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.

Design and UX

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 · 5,153 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

claude-design-premium: Instructions file for Claude Code