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/bestdeejay-design/agent-skillsnpx agentmods add skills/bestdeejay-design/agent-skills/web-replicationWrote 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/bestdeejay-design/agent-skills/web-replication)<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/web-replication"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/web-replication/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/bestdeejay-design/agent-skills/web-replication"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/web-replication.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 | $0.00146 | $0.02023 |
| Opus 5 | $0.00073 | $0.01012 |
| Sonnet 5 | $0.00029 | $0.00405 |
| Haiku 4.5 | $0.00015 | $0.00202 |
Grade C, and why
web-replication scanned grade C with 2 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 6d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
2. Never collect credentials, API keys, or PII Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Collect all image/video/font URLs from the page snapshot, download with curl: How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website Frontend Visual Replication
Origin: Adapted from zai-org/GLM-skills/glmv-web-replication (Apache 2.0).
Agent-browser replaced with Playwright MCP (built into OpenCode).
Prerequisites
This workflow uses Playwright MCP (built into OpenCode via playwright_browser_* tools).
No external dependencies needed.
Authorization Gate (MUST execute first)
Before proceeding, MUST ask the user:
"Do you own this website, or do you have explicit written permission from the owner to replicate it? Unauthorized replication may violate copyright, terms of service, or applicable law."
- If confirmed → proceed
- If cannot confirm → STOP. Suggest building an original design instead.
Scope & Limitations
| Included | NOT Included |
|---|---|
| Page layout & visual styling | Backend / server-side logic |
| Navigation structure | Databases & data stores |
| Publicly visible text & images | Authentication systems |
| CSS/design tokens | API business logic |
| Client-side interaction patterns | Non-public content |
| Static asset files (images, fonts) | Credentials, secrets |
Data handling rules:
- Never scrape behind a login wall
- Never collect credentials, API keys, or PII
- Never reproduce copyrighted content verbatim unless user holds rights
- Respect robots.txt and rate limits
Core Idea
- Recursively explore every public page, record visual content, interactions, and assets into a structured "blueprint" with nested folders representing navigation relationships.
- Build a frontend visual replica based on that blueprint.
- Visually compare and revise.
Blueprint Structure
blueprint/
├── _meta.md # Site metadata
├── _sitemap.md # Sitemap
├── _assets/ # Global assets (fonts, favicon)
├── _navigation_graph.md # Navigation graph (Mermaid)
├── home/ # Homepage
│ ├── _page.md # Page blueprint
│ ├── _full.png # Full-page screenshot
│ ├── _scroll_00.png ~ N.png # Scroll sequence
│ ├── _interactions.md # Interaction records
│ ├── _interactions/ # Interaction state screenshots
│ ├── _assets/ # Page-specific assets
│ ├── products/ # Child pages (reachable from here)
│ │ ├── _page.md
│ │ ├── _full.png
│ │ └── ...
│ └── about/
│ └── ...
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.
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.
- 6d ago First seen · 258 lines · 146 tokens per session scan C 3dd7cff4c0f8
web-replication is a skill published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 146 tokens to every session and 2,023 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (harvests environment variables, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Webdesign
Design and integrate web interfaces via three paths: DirectDesign (write design inline with Anthropic frontend-design philosophy — the default workhorse), native /design + /design-sync Claude Code commands (preferred for code integration and design-system sync), or ClaudeDesign (drive claude.ai/design through…
ui-web
Web UI - glassmorphism, Tailwind, dark mode, accessibility.
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…
impeccable
Use when the user wants distinctive, production-grade frontend design, anti-generic AI aesthetics, UX critique, technical UI audits, or final polish through bundled Impeccable references and an optional upstream detector CLI.
quill-code
Edit the @posthog/quill design system locally and consume the change in products/desktop before it is published to npm. Use when changing quill components/primitives/tokens, when a quill change must be tested inside the Code app, or when the user mentions quill, the design system, the .local-quill tarball, or the…