smart-web-fetch SKILL.md skillA
smart-web-fetch from jkheadley/instar is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jkheadley/instar/smart-web-fetch@v1.0Pins v1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jkheadley/instar
- Path
skills/smart-web-fetch/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0, committed Feb 21, 2026
- Size
- 8,316 bytes
- Repository stars
- 85
- License
- MIT
Fetch web content efficiently by checking llms.txt first, then Cloudflare markdown endpoints, then falling back to HTML. Reduces token usage by 80% on sites that support clean markdown delivery. No external dependencies — installs a single Python script. Trigger words: fetch URL, web content, read website, scrape page, download page, get webpage, read this link.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# smart-web-fetch — Token-Efficient Web Content Fetching Fetching a webpage with the default WebFetch tool retrieves full HTML — navigation menus, footers, ads, cookie banners, and all. For a documentation page, 90% of the tokens go to chrome, not content. This script fixes that by trying cleaner sources first. ## How It Works The fetch chain, in order: 1. **Check `llms.txt`** — Many sites publish `/llms.txt` or `/llms-full.txt` with curated content for AI agents. If present, this is the best source: intentionally structured, no noise. 2. **Try Cloudflare markdown** — Cloudflare's network serves clean markdown for millions of sites via a URL prefix trick. If the site is behind Cloudflare, this returns structured markdown at ~20% of the HTML token cost. 3. **Fall back to HTML** — Standard fetch, with HTML stripped to readable text. Reliable but verbose. The result: typically 60-80% fewer tokens on documentation sites, blog posts, and product pages. --- ## Installation Copy the script into your project's scripts directory: ```bash mkdir -p .claude/scripts ``` Then create `.claude/scripts/smart-fetch.py` with the contents below. --- ## The Script …
Read the whole file at its exact version.
How to install
mdr add jkheadley/instar/smart-web-fetch@sha256:acdaebd7290e4d8fThe line at the top of this page pins the label v1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_pe2vyt76wqajhkr2)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Feb 21, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8316 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jkheadley/instar · 85 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pe2vyt76wqajhkr2 GET https://markdownregistry.com/api/v1/resolve?ref=jkheadley/instar/smart-web-fetch GET https://markdownregistry.com/api/v1/blob/acdaebd7290e4d8f207db3db88b167b84797dd6400fd2e3edf36625343b5405c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.