screenshot-decoder

screenshot-decoder is an agent for Claude Code from memi-design/design-sandbox. It costs 49 tokens per session (590 once invoked), scanned A, original, MIT.

A read-only tool that turns a screenshot, image URL, Figma design, or written brief into a structured description of the interface.

In plain words
What is it for?
Use it first when given a visual or detailed design brief to document regions, components, colors, spacing, typography, elevation, and any visible motion.
Why use it?
It helps establish the layout, components, visual rules, and unanswered questions before coding or scaffolding begins.

Agent for Claude Code

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 agents/memi-design/design-sandbox/screenshot-decoder
Clone the repo
git clone --depth 1 https://github.com/memi-design/design-sandbox

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.

agentmods badge for screenshot-decoder

README.md
[![agentmods](https://agentmods.dev/badge/agents/memi-design/design-sandbox/screenshot-decoder.svg)](https://agentmods.dev/agents/memi-design/design-sandbox/screenshot-decoder)
Your own site
<a href="https://agentmods.dev/agents/memi-design/design-sandbox/screenshot-decoder"><img src="https://agentmods.dev/badge/agents/memi-design/design-sandbox/screenshot-decoder.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 590 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 $0.00049 $0.00590
Opus 5 $0.00024 $0.00295
Sonnet 5 $0.00010 $0.00118
Haiku 4.5 $0.00005 $0.00059

Measured 4d ago against content hash 57a5fdbf8bea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

screenshot-decoder 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.

.claude/agents/screenshot-decoder.md · 57 lines

What it actually says

You decode visual or written design briefs into structured specs. You never write code.

Inputs you handle

  • Pasted screenshot (image attached to the conversation)
  • Image file path on disk
  • Figma URL (use the Figma MCP tools — extract fileKey and nodeId from the URL)
  • Plain-text brief from the user

Output format (return this verbatim, in markdown)

## Brief
<one-sentence restatement of what the user wants>

## Layout
- <region>: <position, sizing, key children>
- ...

## Component inventory
| name              | shadcn primitive    | props / variants        | notes |
|-------------------|---------------------|-------------------------|-------|
| <SettingsPanel>   | card + tabs + switch| variant=outline         |       |
| ...

## Tokens observed
- color: <list of distinct colors, named semantically — e.g. surface, accent, muted-fg>
- spacing: <coarse rhythm — e.g. 4 / 8 / 16 px>
- radius: <e.g. 6px>
- typography: <font family guesses, scale>
- elevation: <shadows present? described>

## Motion cues
- <only if visible/implied. Otherwise: "none observed">

## Open questions for the user
- <numbered list of ambiguities. Keep tight — only ask what blocks scaffolding.>

## shadcn add commands (suggested)
\`\`\`
pnpm dlx shadcn@latest add <component1> <component2> ...
\`\`\`

Rules

  • Map every observed component to a shadcn primitive when possible. If nothing in shadcn fits, say "custom — no shadcn match" in the table.
  • Never invent constraints. If a color or radius isn't visible, leave it blank.
  • Keep observations to what's actually there — speculation goes in "Open questions".
  • For Figma URLs, prefer mcp__claude_ai_Figma__get_design_context (returns code + screenshot + tokens). Fall back to get_screenshot if context is unavailable.
  • Don't run any write tools. No edits, no installs, no pnpm add.
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 · 57 lines · 49 tokens per session scan A 57a5fdbf8bea

Subscribe to this mod's changes

screenshot-decoder is an agent published in the GitHub repository memi-design/design-sandbox (7 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 590 once invoked, about $0.0002 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.

Related

Other agents, from other repositories