agentmods.dev

exact-clone-intake

A workflow for copying a webpage from a URL with high visual accuracy. It first inspects the original, reuses available sources when allowed, or rebuilds the page from captured evidence when necessary.

In plain words
What is it for?
It is for cloning, embedding, capturing, or reconstructing pages from URLs, including pages that need session-aware inspection or a bounded frontend rebuild.
Why use it?
It makes webpage cloning more reliable by checking the source and verifying the result before considering the work finished.

Skill for Claude CodeCodex

4 2mo ago A scan 74 tokens original MIT
View the source file jongko54/webEmbedding
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/jongko54/webembedding/exact-clone-intake
Any agent
npx skills add jongko54/webEmbedding --skill exact-clone-intake
Clone the repo
git clone --depth 1 https://github.com/jongko54/webEmbedding

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 799 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 $0.00074 $0.00799
Opus 5 $0.00037 $0.00400
Sonnet 5 $0.00015 $0.00160
Haiku 4.5 $0.00007 $0.00080

Measured 2d ago against content hash c2fc0937f1c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

exact-clone-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 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.

bundle/source-first-clone/skills/exact-clone-intake/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Exact Clone Intake

Treat requests like 그대로 가져와줘, 완전 똑같이, same, exact, as-is, and clone this as source-first clone requests.

Do not use this skill for generic URL summarization, data scraping, localhost debugging, original page design, package maintenance, or requests to bypass auth, paywalls, captcha, ownership, or license boundaries.

This skill is paired with the source-first-clone MCP server. It is meant for general AI coding workflows, not a single framework. The important behavior is: inspect first, capture evidence, reuse when allowed, rebuild only when needed, and verify the output instead of trusting prompt-only generation.

Workflow

  1. Inspect the reference URL before writing code.
  2. Use MCP tools in this order:
    • clone_reference_url when you want the full URL-to-clone workflow in one pass
    • detect_runtime_capabilities when session-aware capture might be needed
    • inspect_url
    • discover_embed_candidates
    • trace_runtime_sources when static HTML is not enough
    • classify_clone_mode
    • capture_reference_bundle when exact reuse is unclear or blocked
    • build_rebuild_scaffold when exact reuse is blocked and you need bounded reconstruction artifacts
    • build_reproduction_bundle after capture when you need an exact reuse output package
    • plan_reproduction_path
    • generate_embed_snippet only when an actual embed path exists
    • verify_fidelity_report when comparing a reproduced result
  3. Prefer these outcomes in order:
    • direct iframe reuse of the original page when frameable
    • original embed or preview
    • original remix, export, or source
    • bounded rebuild from captured evidence with a fidelity report
  4. Respect license and ownership signals. If the page is not clearly reusable, say so before cloning.

Output rules

  • Do not call a rebuild exact unless it is actually direct source reuse.
  • If an original preview or embed exists, use it instead of recreating the page.
  • If the original source is private, explain what is missing and what permission or export is needed.
  • When a rebuild is used, report the verification score and the strongest remaining gaps.
  • For public demos, prefer neutral examples such as documentation or public landing pages over brand-sensitive clone claims.

Read the full file on GitHub · 54 lines

Files

What ships with it

1 file 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. 2d ago First seen · 54 lines · 74 tokens per session scan A c2fc0937f1c3

Subscribe to this mod's changes

exact-clone-intake is a skill published in the GitHub repository jongko54/webEmbedding (4 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 799 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.

Browser automationFrontendai-agentbrowser-captureharmcpplaywright
Related

Other skills, from other repositories

playwright-cli

Automate browser interactions, test web pages and work with Playwright tests.

microsoft/playwright · 19 tokens

scrapling-official

Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…

D4Vinci/Scrapling · 80 tokens

playwright-dev

Explains how to develop Playwright - add APIs, MCP tools, CLI commands, and vendor dependencies.

microsoft/playwright · 25 tokens

agent-browser

Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms — for verification tasks, not unattended automation.

paperclipai/paperclip · 40 tokens

stagehand-facade

Browse, navigate, inspect, screenshot, and automate websites with the exact fx tools mcpstagehandrun, mcpstagehandsnapshot, and mcpstagehandscreenshot.

browserbase/stagehand · 42 tokens

playwriter

Control the user own Chrome browser via Playwriter extension with Playwright code snippets in a stateful local js sandbox. Use this over other Playwright MCPs to automate the browser — it connects to the user's existing Chrome instead of launching a new one. Use this cli for navigating JS-heavy websites (Instagram…

remorses/playwriter · 92 tokens