studio

studio is a command for coding agents from Manavarya09/design-extract. It costs 0 tokens per session (349 once invoked), scanned A, original, MIT.

A local browser-based editor for an extracted website’s design tokens, such as colours, spacing and typography settings. It lets you preview those changes on real components and export the edited design system.

In plain words
What is it for?
Use it to adjust an extracted design system, preview light and dark themes, inspect animations, and export tokens as DTCG, CSS variables or a Tailwind theme.
Why use it?
It removes the need to edit design values blindly in code. You can see how token changes affect a page and components before exporting them.

Command

Part of the designlang plugin — 2 skills, 14 commands shipped together

Install

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.

agentmods
npx agentmods add commands/manavarya09/design-extract/studio
Clone the repo
git clone --depth 1 https://github.com/Manavarya09/design-extract

Or install designlang, the plugin that ships this one along with the rest of its 2 skills, 14 commands.

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.

agentmods badge for studio

README.md
[![agentmods](https://agentmods.dev/badge/commands/manavarya09/design-extract/studio.svg)](https://agentmods.dev/commands/manavarya09/design-extract/studio)
Your own site
<a href="https://agentmods.dev/commands/manavarya09/design-extract/studio"><img src="https://agentmods.dev/badge/commands/manavarya09/design-extract/studio.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 349 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00349
Opus 5 $0.00000 $0.00175
Sonnet 5 $0.00000 $0.00070
Haiku 4.5 $0.00000 $0.00035

Measured 4d ago against content hash 098126fd7d1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

studio 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.

commands/studio.md · 33 lines

What it actually says

Launch designlang studio, a tiny local web app that turns the most recent extraction into a living, editable design system. Editing a token restyles a wall of real components and a rebuilt page instantly; you can toggle a generated dark mode, inspect easing curves and choreography in the Motion tab, and export the edited system back out as DTCG tokens, CSS variables, and a Tailwind theme — or copy a shareable link that encodes the edits.

npx designlang studio $ARGUMENTS

This starts a local HTTP server (default port 4837) and prints a URL. Tell the user to open it in their browser. It reads the latest *-design-tokens.json from ./design-extract-output/ by default — if there is no extraction yet, run /extract <url> or /site <url> first.

Useful flags via $ARGUMENTS:

Flag Effect
--dir <dir> directory to read the latest extraction from
--port <n> port for the local server (default 4837)

The server runs until the user stops it (Ctrl+C). Do not block on it — surface the URL and let the user drive.

Full reference: https://github.com/Manavarya09/design-extract#full-cli-reference

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.

  1. 4d ago First seen · 33 lines · 0 tokens per session scan A 098126fd7d1f

Subscribe to this mod's changes

studio is a command published in the GitHub repository Manavarya09/design-extract (4,000 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 349 tokens. 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.