frameit: Command for Claude Code

.claude/commands/reproduce-image.md

reproduce-image is a command for Claude Code from edspencer/frameit. It costs 12 tokens per session (2,053 once invoked), scanned A, original, MIT.

A command for examining an Open Graph image—an image used when a webpage is shared—and rebuilding its layout with FrameIt.

In plain words
What is it for?
Use it to inspect an image’s regions, text placement, fonts, colors, spacing, and alignment before recreating it.
Why use it?
It turns a visual reference into a documented layout plan, making it easier to reproduce the image accurately.

Command for Claude Code

Written for Claude Code: arguments in frontmatter.

This is edspencer/frameit's own configuration. It tells Claude Code how to work on frameit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything frameit configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/ed/Code/thumbnail-generator/src/lib/constants/layouts.ts.

Reuse

Borrowing it

Nothing to install: this file belongs to edspencer/frameit. 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/edspencer/frameit/main/.claude/commands/reproduce-image.md
Clone the repo
git clone --depth 1 https://github.com/edspencer/frameit

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 reproduce-image

README.md
[![agentmods](https://agentmods.dev/badge/commands/edspencer/frameit/reproduce-image/github.svg)](https://agentmods.dev/commands/edspencer/frameit/reproduce-image)
Your own site
<a href="https://agentmods.dev/commands/edspencer/frameit/reproduce-image"><img src="https://agentmods.dev/badge/commands/edspencer/frameit/reproduce-image/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.

agentmods 80×15 button for reproduce-image

Your own site · 80×15
<a href="https://agentmods.dev/commands/edspencer/frameit/reproduce-image"><img src="https://agentmods.dev/badge/commands/edspencer/frameit/reproduce-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,053 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.02053
Opus 5 $0.00006 $0.01026
Sonnet 5 $0.00002 $0.00411
Haiku 4.5 $0.00001 $0.00205

Measured 10d ago against content hash b2f34e39a535, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reproduce-image 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 10d 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/commands/reproduce-image.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reproduce Image Command

You are tasked with analyzing an Open Graph (OG) image and reproducing it using FrameIt's layout system.

Input

The user has provided: {{image}}

Process

Follow these steps in order:

1. Load the Image

First, determine what type of input was provided:

  • If it's a filename (e.g., "clerk.jpg", "boring-launch.png"), look for it in ./layouts/original/ directory
  • If it's a relative or absolute path, read directly from that path
  • If it's a URL starting with http:// or https://, fetch the image from the URL

Use the Read tool to load the image and display it for analysis.

2. Thorough Visual Analysis

Analyze the image comprehensively and provide:

Layout Structure:

  • Overall layout pattern (centered, split, sidebar, etc.)
  • Number of distinct sections/regions
  • Spatial relationships between elements

Text Elements:

  • Identify all text content with approximate positioning (top-left, center, bottom-right, etc.)
  • Font sizes relative to canvas (estimate as percentages)
  • Font weights (light, normal, semi-bold, bold, extra-bold)
  • Text alignment (left, center, right)
  • Text colors (estimate hex values)
  • Line heights and spacing

Visual Elements:

  • Brand logos and icons (IMPORTANT: Replace with FrameIt assets)
    • Square icons → use FrameIt icon (/frameit-icon.png)
    • Wide/rectangular logos → use FrameIt logo (/frameit-logo.png)
    • Choose based on aspect ratio of original
  • Other graphics or decorative elements
  • Positioning and sizing relative to canvas

Background:

  • Solid color (estimate hex)
  • Gradient (direction, colors)
  • Pattern or texture
  • Estimate closest match from our Tailwind color palette or gradient library

Spacing & Layout:

  • Margins and padding (estimate as percentages)
  • Element anchoring (which corner/edge elements are positioned from)
  • Maximum widths for text wrapping

3. Propose HTML/CSS Flex Layout

Based on your analysis, describe how you would implement this using modern HTML/CSS flex layouts:

Read the full file on GitHub · 238 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.

  1. 10d ago First seen · 238 lines · 12 tokens per session scan A b2f34e39a535

Subscribe to this mod's changes

reproduce-image is a command published in the GitHub repository edspencer/frameit (10 stars, last pushed 9mo ago), licensed MIT. It adds 12 tokens to every session and 2,053 once invoked, about $0.0001 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.