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/valtterimelkko/agent-workflow-skillsnpx agentmods add skills/valtterimelkko/agent-workflow-skills/webfetch-skillWrote 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/valtterimelkko/agent-workflow-skills/webfetch-skill)<a href="https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/webfetch-skill"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/webfetch-skill/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/valtterimelkko/agent-workflow-skills/webfetch-skill"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/webfetch-skill.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 | $0.00116 | $0.02068 |
| Opus 5 | $0.00058 | $0.01034 |
| Sonnet 5 | $0.00023 | $0.00414 |
| Haiku 4.5 | $0.00012 | $0.00207 |
Grade A, and why
webfetch-skill 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 8d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Fetch
Fetch and analyze web content by calling a specialized sub-agent that uses the webfetch script.
Use this as a clean single-page / few-page extraction tier:
- prefer native
web_fetchfor quick cooperative pages - prefer this skill when you want cleaner markdown extraction, comparison across a few URLs, or extraction from article-like pages
- if the page is challenge-blocked or JS-only, recover that URL with
camofoxbefore escalating to any paid proxy path
Quick Start
To fetch and analyze web content, invoke the webfetch sub-agent:
Fetch a single URL:
Fetch and summarize: https://example.com
Fetch multiple URLs (max 5):
Fetch and compare: https://example.com and https://example2.com
Analyze specific content:
What are the main points on: https://example.com/article
Extract specific information:
Extract all email addresses from: https://example.com/contact
The sub-agent will:
- Fetch the URL(s) using the webfetch script
- Read the extracted markdown content
- Provide AI analysis based on your prompt
Escalation contract
Keep the order narrow and cheap:
- Try native
web_fetchor this script workflow first. - If the target page is blocked by Cloudflare, challenge pages, or blank JS rendering, retry that URL with
camofox. - If
camofoxalso fails and the blocked URL is genuinely important, ask before usingresidential-proxy.
Do not automatically turn a small fetch task into a proxy-backed workflow.
Prerequisites
The webfetch script requires these Python packages:
pip install --break-system-packages trafilatura requests beautifulsoup4
trafilatura - Main content extraction and HTML→markdown conversion requests - HTTP client for fetching URLs beautifulsoup4 - Link and image extraction
How It Works
- Skill triggers when you ask to fetch web content
- Sub-agent invoked via Task tool
- Script executes webfetch.py to fetch and extract content
- Sub-agent analyzes the markdown output and provides intelligent response
- Results returned with summaries, extractions, or answers
What ships with it
2 files 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.
- 8d ago First seen · 260 lines · 116 tokens per session scan A 04d9415cffb6
webfetch-skill is a skill published in the GitHub repository valtterimelkko/agent-workflow-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 116 tokens to every session and 2,068 once invoked, about $0.0006 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.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…