webfetch

A self-hosted web-search plugin for coding agents. It searches the web, fetches pages, ranks results, and can save findings using a local search pipeline.

In plain words
What is it for?
Searching for information, fetching web pages, ranking findings, saving research results, checking search status, and reviewing search-cost savings.
Why use it?
It gives agents a way to research online while reusing cached results to reduce repeated search work and input size. It can use DuckDuckGo without requiring an API key.

Plugin for Claude Code

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 plugins/firish/webfetch/marketplace
Claude Code
/plugin marketplace add firish/webfetch
Clone the repo
git clone --depth 1 https://github.com/firish/webfetch

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

webfetch 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 yesterday.

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.

.claude-plugin/marketplace.json · 17 lines

What it actually says

{
  "name": "webfetch",
  "owner": {
    "name": "Rishi Gulati"
  },
  "description": "Self-hosted web search for LLM agents - same accuracy as hosted web_search at a third of the cost",
  "plugins": [
    {
      "name": "webfetch",
      "source": "./plugin",
      "description": "web_search, fetch_url, save_finding, status, and savings_report tools backed by a local search -> fetch -> rank pipeline with semantic caching. Up to 8x fewer input tokens and 3x lower cost than hosted web search. Needs uv; API keys optional (DDG works with none).",
      "category": "search",
      "tags": ["web-search", "mcp", "cache", "cost-optimization", "research"]
    }
  ]
}
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. yesterday First seen · 17 lines scan A e52848590edb

Subscribe to this mod's changes

webfetch is a plugin published in the GitHub repository firish/webfetch (55 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.