KaryawanSurgaKaryawanSurga/tokensaver-plugin/skills/web-snapshot/SKILL.md

web-snapshot

Skill1 starsChanged 45 days agoMITView on GitHub

Read web pages as clean markdown. Use when you need documentation, articles, release notes, issues, or any URL content without flooding the context with raw HTML — including pages that were recently redesigned.

In this repository9 other files it gives its agents.
- commitsmithSkill
- context-budgetSkill
- gatewaySkill
- injection-guardSkill
- json-lensSkill
- log-tailSkill
- repo-mapSkill
- secret-scanSkill
- tokensaverSkill

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Call snapshot with the URL and a budget suited to the task (4000 is a good default).
line 26
Very specific:
Use adaptive: true for pages you revisit: the tool remembers the content structure and recovers it after a redesign.
line 27
Very specific:
If a page fails to extract, try readability: false for the full structure.
line 29

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Web snapshot

Fetch a URL and get readable markdown: main content extracted, navigation and ads removed, links resolved, output capped by a token budget.

MCP tools

Tool	Use it for
`snapshot`	One page → markdown with title, source metadata, token count, truncation flag.
`extract_links`	The links on a page (optionally same-origin only) for planning what to read next.

Workflow

Call snapshot with the URL and a budget suited to the task (4000 is a good default).
Use adaptive: true for pages you revisit: the tool remembers the content structure and recovers it after a redesign.
Request links: true when you need to choose the next page.
If a page fails to extract, try readability: false for the full structure.

CLI fallback

npx -y mcp-web-snapshot https://example.com --budget 3000
npx -y mcp-web-snapshot https://docs.example.com/guide --adaptive

Tips

Respect the page's terms and robots policy; this tool is for reading, not bulk crawling.
Adaptive memory lives at ~/.mcp-web-snapshot/memory.json (override with --memory).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free