fetch

A tool for fetching the useful text from a web page while removing most HTML, scripts, styles, menus, and footers. It can return a short, full, or metadata-only extraction.

In plain words
What is it for?
Use it to inspect documentation, articles, or other URLs, preview a page before deeper research, reuse cached results, or avoid caching sensitive pages.
Why use it?
It provides readable page content with much less irrelevant data, which makes quick web research more efficient.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/grainulation/grainulator/fetch
Any agent
npx skills add grainulation/grainulator --skill fetch
Clone the repo
git clone --depth 1 https://github.com/grainulation/grainulator

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 949 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.00949
Opus 5 $0.00014 $0.00475
Sonnet 5 $0.00005 $0.00190
Haiku 4.5 $0.00003 $0.00095

Measured 2d ago against content hash 99952447400b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fetch 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 2d 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.

skills/fetch/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fetch -- Ad-hoc URL fetch with smart extraction

Pulls a URL's main content (title, description, body paragraphs) without the HTML boilerplate. Delegates to silo's smart-fetch MCP tool, which strips scripts/styles/nav/footer and targets <main> or <article> regions. Typical reduction: 80-99% vs raw HTML.

Arguments

$ARGUMENTS

Expected: /fetch <url> [--mode auto|concise|full|meta-only] [--no-cache] [--privacy]

  • --mode auto (default): tries concise extraction, falls back to full if quality degrades
  • --mode concise: caps body at ~2KB
  • --mode full: returns all extracted paragraphs
  • --mode meta-only: only title + description (smallest)
  • --no-cache: skip local cache read, force network fetch
  • --privacy: don't write to cache (use for sensitive URLs)

When to use

  • Quick reference: "what does this page say" — /fetch <url> beats opening a browser
  • Before witnessing: peek at content before committing to /witness (which creates a claim)
  • Third-party pages: docs sites, blog posts, research articles
  • Re-reading: cache hits are ~1ms; great for iterating on content you've already fetched

When NOT to use

  • Confluence: use /pull — structured API is better than HTML scraping
  • DeepWiki: use /pull deepwiki — it already has a cleaner path
  • Authenticated pages: smart-fetch doesn't do auth. Use farmer for approval-gated flows.
  • PDFs, images, JSON: smart-fetch rejects non-HTML content types with unsupported-content-type

Instructions

  1. Call mcp__silo__silo_smart-fetch with the URL and parsed flags.

  2. If the response quality is "failed" (empty body, SPA, link list, HTTP error), tell the user:

    • What the reported quality was
    • Any warnings returned
    • Suggest retrying with --mode full or raw WebFetch as a fallback
  3. Display the extracted content in a readable format:

    • Title, description
    • Full content (or first N lines if very long)
    • Size reduction metric and cache hit/miss status

Read the full file on GitHub · 86 lines

Changes

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.

  1. 2d ago First seen · 86 lines · 27 tokens per session scan A 99952447400b

Subscribe to this mod's changes

fetch is a skill published in the GitHub repository grainulation/grainulator (87 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 949 once invoked, about $0.0001 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 2026-08-30.