web_fetcher_skill

web_fetcher_skill is a skill for Claude Code, Codex from 81120/light-agent. It costs 33 tokens per session (266 once invoked), scanned A, original, MIT.

A web-fetching skill that retrieves text, raw HTML, or JSON from an HTTP or HTTPS URL.

In plain words
What is it for?
Fetching news articles, extracting webpage text, downloading page HTML, and retrieving JSON from web APIs.
Why use it?
It gives the coding agent a defined way to read web pages and API responses, including pages that are not already in the project.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/81120/light-agent/web_fetcher_skill
Any agent
npx skills add 81120/light-agent --skill web_fetcher_skill
Clone the repo
git clone --depth 1 https://github.com/81120/light-agent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for web_fetcher_skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/81120/light-agent/web_fetcher_skill.svg)](https://agentmods.dev/skills/81120/light-agent/web_fetcher_skill)
Your own site
<a href="https://agentmods.dev/skills/81120/light-agent/web_fetcher_skill"><img src="https://agentmods.dev/badge/skills/81120/light-agent/web_fetcher_skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 266 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 5.1 $0.00033 $0.00266
Opus 5 $0.00016 $0.00133
Sonnet 5 $0.00007 $0.00053
Haiku 4.5 $0.00003 $0.00027

Measured 6d ago against content hash 57d8eae3beee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

web_fetcher_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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fetch.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

agent/skills/web_fetcher_skill/SKILL.md · 54 lines

What it actually says

Web Fetcher

Use Cases

Use this skill when you need web content:

  • Fetch news article content
  • Extract text from webpages
  • Retrieve JSON from API endpoints

Steps

  1. Prepare the target URL.
  2. Run node scripts/fetch.js <url> [format].
  3. The script returns webpage content.

Command

node scripts/fetch.js <url> [format]
  • url: target URL (required)
  • format: output format, text (default) or html

Output Format

  • Success: webpage content (text or HTML)
  • Failure: error message

Examples

# Fetch page text content
node scripts/fetch.js "https://example.com/article"

# Fetch raw HTML
node scripts/fetch.js "https://example.com" html

# Fetch API JSON response
node scripts/fetch.js "https://api.github.com/users/github"

Notes

  • Some websites may block scraping
  • Large pages may take longer to fetch
  • Only HTTP/HTTPS is supported
Files

What ships with it

1 file 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.

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. 6d ago First seen · 54 lines · 33 tokens per session scan A 57d8eae3beee

Subscribe to this mod's changes

web_fetcher_skill is a skill published in the GitHub repository 81120/light-agent (24 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 266 once invoked, about $0.0002 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.