screenshot-to-interface

screenshot-to-interface is a skill for Claude Code, Codex from cmdr-chara/codex-toolkit. It costs 72 tokens per session (1,797 once invoked), scanned A, original, MIT.

A workflow for rebuilding a web interface from screenshots or other visual references.

In plain words
What is it for?
Recreating pages, screens, components, or user flows from supplied screenshots and checking the result against the references.
Why use it?
It turns a visual example into maintainable interface code while accounting for layout, responsive behavior, assets, and accessibility.

Skill for Claude CodeCodex

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 skills/cmdr-chara/codex-toolkit/screenshot-to-interface
Any agent
npx skills add cmdr-chara/codex-toolkit --skill screenshot-to-interface
Clone the repo
git clone --depth 1 https://github.com/cmdr-chara/codex-toolkit

Made for: Claude Code, Codex.

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 screenshot-to-interface

README.md
[![agentmods](https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/screenshot-to-interface.svg)](https://agentmods.dev/skills/cmdr-chara/codex-toolkit/screenshot-to-interface)
Your own site
<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/screenshot-to-interface"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/screenshot-to-interface.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,797 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 $0.00072 $0.01797
Opus 5 $0.00036 $0.00898
Sonnet 5 $0.00014 $0.00359
Haiku 4.5 $0.00007 $0.00180

Measured 4d ago against content hash e8e6db40ecd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

screenshot-to-interface 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.

skills/screenshot-to-interface/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Screenshot to Interface

Treat references as evidence, not as a bitmap to trace blindly. Reconstruct the underlying layout and behavior while preserving maintainability and rights.

Trigger boundary

Use this skill for:

  • implementing a page, screen, component, or flow from screenshots;
  • translating a design comp into responsive components;
  • auditing why an implementation differs from its reference;
  • inferring a coherent component/system model from multiple visual states.

Do not trigger for:

  • deciding an original visual direction without a reference—use product-design-director;
  • a production web/mobile audit unrelated to reference fidelity—use the platform builder;
  • extracting or redistributing protected assets without permission;
  • image OCR or screenshot transcription where no interface reconstruction is requested.

Required inputs

Obtain or record as unknown:

  1. all reference images and their source/provenance;
  2. pixel dimensions, device scale factor, viewport, orientation, theme, locale, and state if known;
  3. target repository, stack, routes, and existing design system;
  4. required interactions, responsive range, browsers/devices, and accessibility target;
  5. asset rights and available original logos/icons/fonts/images;
  6. acceptable fidelity tolerance and whether content may be adapted.

Do not infer one desktop screenshot as the complete responsive specification.

Provenance

This skill is an original restructuring that selectively adapts visual-reference and fidelity concepts from Leonxlnx/taste-skill. Read references/provenance.md and preserve the root notice.

Safety baseline

  • Inspect repository and working-tree state before editing.
  • Reuse existing tokens/components when they can express the reference without distortion.
  • Do not replace project architecture, framework, or styling system solely for visual convenience.
  • Do not embed screenshots as the interface, hard-code coordinates for one viewport, or use inaccessible canvas/text images for ordinary UI.
  • Do not download fonts/assets from a reference without rights and license evidence.
  • Preserve user code and keep generated or broad formatting changes out of the diff.

Read the full file on GitHub · 205 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 205 lines · 72 tokens per session scan A e8e6db40ecd6

Subscribe to this mod's changes

screenshot-to-interface is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 7d ago), licensed MIT. It adds 72 tokens to every session and 1,797 once invoked, about $0.0004 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.