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/zai-org/GLM-skillsnpx agentmods add skills/zai-org/glm-skills/glmv-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/zai-org/glm-skills/glmv-web-replication)<a href="https://agentmods.dev/skills/zai-org/glm-skills/glmv-web-replication"><img src="https://agentmods.dev/badge/skills/zai-org/glm-skills/glmv-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/zai-org/glm-skills/glmv-web-replication"><img src="https://agentmods.dev/badge/skills/zai-org/glm-skills/glmv-web-replication.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00151 | $0.04139 |
| Opus 5.5 | $0.00060 | $0.01656 |
| Sonnet 5.5 | $0.00030 | $0.00828 |
| Haiku 4.5 | $0.00015 | $0.00414 |
Grade A, and why
glmv-web-replication scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
10. Assets should be downloaded whenever possible. Use `curl` to download images, and use `agent-browser eval` or Playwright MCP to extract SVG source code and save it. All failed downloads must be recorded together with How it starts
The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website Frontend Visual Replication
Prerequisites
This workflow depends on either Playwright MCP or the agent-browser skill. As long as at least one of them is installed and available, the workflow can run normally. If neither is available in your environment, remind the user to install one.
Authorization Gate (MUST execute first)
Before proceeding, the agent 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 the user confirms authorization → proceed.
- If the user cannot confirm → STOP. Do not proceed with replication. Suggest alternatives (e.g., building an original design inspired by general layout patterns).
Scope & Limitations
This skill replicates FRONTEND VISUAL PRESENTATION only. Specifically:
| Included | NOT Included |
|---|---|
| Page layout & visual styling | Backend / server-side logic |
| Navigation structure | Databases & data stores |
| Publicly visible text & images | Authentication systems / sessions |
| CSS/design tokens | API business logic |
| Client-side interaction patterns | Non-public or behind-login content |
| Static asset files (images, fonts) | Credentials, secrets, or API keys |
Data handling rules:
- Never scrape behind a login wall. Only capture publicly accessible pages.
- Never collect or store credentials, API keys, session tokens, or personal data (PII).
- Never reproduce copyrighted content verbatim (articles, copy text) unless the user holds rights.
- Respect robots.txt and rate limits. If the site signals crawl restrictions, honor them.
- Output is for reference & mockup purposes unless the user has confirmed full rights.
Core Idea
- Recursively explore every public page of the target website, systematically record its visual content, client-side interaction logic, and publicly available asset files, and organize everything into a structured “website replication blueprint.” This blueprint should comprehensively include detailed information for each page, and naturally map the site’s navigation relationships through folder hierarchy. Specifically, during exploration, use nested folders to organize and record the collected page information: represent the current page as a folder, and represent all pages reachable from it as child folders. At the same time, save that page’s screenshots, component interaction records, and related asset files inside the page folder. With this structure, the final blueprint will clearly present both the content and interaction details of each page, while also implicitly reflecting the website’s overall information architecture and navigation paths.
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.
- 1mo ago First seen · 307 lines · 151 tokens per session scan A e7e79c2abbb1
glmv-web-replication is a skill published in the GitHub repository zai-org/GLM-skills (476 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 151 tokens to every session and 4,139 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
vision-skills
Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/htmlshot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long…
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
display-glasses-with-jetpack-compose-glimmer
Provides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI toolkit. Covers Glimmer design principles, workflows, and interaction models for the glasses form factor. Use this skill to build an Android XR Augmented Experience app with Jetpack Compose Glimmer.…
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
visual-edit
Open and collaboratively edit a running local app in Design, with shared fallback previews and source handoff. Use when the user asks to inspect, share, or edit a real local app in Design.
visual-plan
Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.