Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PMDevSolutions/Aureliusnpx agentmods add skills/pmdevsolutions/aurelius/screenshot-intakeWrote 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.
[](https://agentmods.dev/skills/pmdevsolutions/aurelius/screenshot-intake)<a href="https://agentmods.dev/skills/pmdevsolutions/aurelius/screenshot-intake"><img src="https://agentmods.dev/badge/skills/pmdevsolutions/aurelius/screenshot-intake/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.
<a href="https://agentmods.dev/skills/pmdevsolutions/aurelius/screenshot-intake"><img src="https://agentmods.dev/badge/skills/pmdevsolutions/aurelius/screenshot-intake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.04586 |
| Opus 5.5 | $0.00000 | $0.01834 |
| Sonnet 5.5 | $0.00000 | $0.00917 |
| Haiku 4.5 | $0.00000 | $0.00459 |
Grade A, and why
screenshot-intake 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot Intake — Structured Discovery
Purpose
Gather everything needed to build a React/Vue/Svelte/React Native app from screenshots or a live URL in a single structured pass. Captures pages, analyzes them with Claude vision, asks the user only what cannot be derived, and writes .claude/plans/build-spec.json that downstream phases consume without re-asking questions.
When to Use
- First phase of the
/build-from-screenshotpipeline - A user provides a URL and says "build something like this" or "clone this site"
- A user provides screenshot image paths and wants to build from them
- No Figma or Canva source is available, only screenshots or live pages
Inputs
- One of:
- URL (
http://orhttps://) — captured via browser MCP - One or more image file paths (
.png,.jpg,.webp)
- URL (
- Optional: Existing project directory to integrate into
- Reads:
.claude/pipeline.config.jsonfor screenshot settings underscreenshot
Process
Step 1: Determine Source Mode and Capture
digraph capture_flow {
"Input received" [shape=diamond];
"URL mode" [shape=box];
"File mode" [shape=box];
"Chrome DevTools MCP available?" [shape=diamond];
"Use Chrome DevTools MCP" [shape=box];
"Playwright MCP available?" [shape=diamond];
"Use Playwright MCP" [shape=box];
"Ask user to provide screenshots" [shape=box];
"Validate image files" [shape=box];
"Save to source dir" [shape=box];
"Input received" -> "URL mode" [label="starts with http"];
"Input received" -> "File mode" [label="otherwise"];
"URL mode" -> "Chrome DevTools MCP available?";
"Chrome DevTools MCP available?" -> "Use Chrome DevTools MCP" [label="yes"];
"Chrome DevTools MCP available?" -> "Playwright MCP available?" [label="no"];
"Playwright MCP available?" -> "Use Playwright MCP" [label="yes"];
"Playwright MCP available?" -> "Ask user to provide screenshots" [label="no"];
"File mode" -> "Validate image files";
"Use Chrome DevTools MCP" -> "Save to source dir";
"Use Playwright MCP" -> "Save to source dir";
"Validate image files" -> "Save to source dir";
}
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.
- 13d ago Changed · +1 lines 85fa0033827f
- 2mo ago First seen · 429 lines · 0 tokens per session scan A 1c15d2acbae0
screenshot-intake is a skill published in the GitHub repository PMDevSolutions/Aurelius (9 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,586 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 2026-09-04.
screenshot-intake compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| screenshot-intakePMDevSolutions/Aurelius | Skill | 9 | yesterday | MIT | A | 0 | Claude Code |
| figma-codegenawdr74100/figwright | Skill | 1.3k | yesterday | MIT | A | 145 | Claude Code, Codex |
| figma-buildawdr74100/figwright | Skill | 1.3k | yesterday | MIT | A | 180 | Claude Code, Codex |
| mk:figmangocsangyem/MeowKit | Skill | 15 | 6d ago | MIT | A | 99 | Claude Code |
| build-designoyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 27 | Claude Code |
| figma-web-capturememi-design/design-skills | Skill | 7 | 1mo ago | MIT | A | 33 | Claude Code, Codex |
| design-qanaver/design-to-ui | Skill | 8 | 2mo ago | Apache-2.0 | A | 243 | Claude Code |