clone-website

A command for studying a website from its URL and producing a detailed plan for recreating its interface and structure. It can target web or mobile projects and supports several levels of similarity.

In plain words
What is it for?
Use it to document a site’s layout and information structure before rebuilding it in a chosen technology, such as Next.js or Expo.
Why use it?
It separates visual and structural analysis from implementation, making it easier to decide what should be copied, adapted, or used only as inspiration.

Command

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/adilkalam/orca/clone-website
Clone the repo
git clone --depth 1 https://github.com/adilkalam/orca
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,632 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 $0.00022 $0.01632
Opus 5 $0.00011 $0.00816
Sonnet 5 $0.00004 $0.00326
Haiku 4.5 $0.00002 $0.00163

Measured 2d ago against content hash 51cef696a1af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clone-website 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 2d 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/clone-website.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/clone-website – SAME.dev‑style Website Cloner (Spec‑First)

Goal: Use SAME.dev's cloning playbook (via web analysis) to produce a high‑fidelity UI/structure spec for a target site, then hand off to OS 7.0 unified /orca pipeline for implementation. This command focuses on spec and structure, not blindly autogenerated code.


1. Inputs & Modes

Request: $ARGUMENTS

Interpret as:

  • Primary: url – required (the site to study/clone).
  • Optional: clone_mode – one of:
    • "exact" – 1:1 UI/structure (within legal/ethical bounds).
    • "similar" – keep patterns, adjust brand tokens.
    • "inspired" – use as inspiration, new design.
    • "structure" – IA/layout only, new visuals.

If only a URL is provided (no mode), ask via AskUserQuestion:

  • Whether they want to "clone" the UI and at what level (exact/similar/inspired/structure).
  • Which stack they're targeting (Nextjs/web vs Expo/mobile).

Image Path Detection

If the argument appears to be a file path (contains /, ends in .png, .jpg, .jpeg, .webp, .gif, or .svg):

  1. Confirm the file exists using Read tool
  2. Instead of web analysis, delegate to screenshot-analyzer agent:
    Agent({
      subagent_type: 'screenshot-analyzer',
      description: 'Analyze screenshot for clone spec',
      prompt: 'Analyze this screenshot: <path>. Produce component inventory and implementation spec.'
    })
    
  3. Use the screenshot analysis output as the basis for the clone spec (Step 4)
  4. Skip Step 3 (Web Analysis) entirely -- go directly to Step 4 (Structured Clone Spec)

Present to user: "Detected an image path instead of URL. Routing to screenshot analysis..."


2. SAME.dev Safety & Clarification (MANDATORY)

Before any analysis:

  1. Safety checks (from SAME.dev spec):
    • NEVER clone sites with ethical, legal, pornographic, or privacy concerns.
    • NEVER clone login/auth pages or flows that could be used for phishing.
    • If the target flow is behind auth, ask user to provide post-login screenshots instead.

Read the full file on GitHub · 181 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. 2d ago First seen · 181 lines · 22 tokens per session scan A 51cef696a1af

Subscribe to this mod's changes

clone-website is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,632 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.