A web-search tool that searches Google or DuckDuckGo, opens result pages, and extracts their text as readable Markdown.

Use it to search the internet, inspect search results, visit selected pages, and collect readable page content for an AI agent.

It saves you from manually browsing pages when an answer depends on current information or sites that need a browser to load.

web-search — Skill for Claude Code and Codex by ogulcancelik

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.

Any agent

npx skills add ogulcancelik/agent-skills --skill web-search

Clone the repo

git clone --depth 1 https://github.com/ogulcancelik/agent-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ogulcancelik/agent-skills/web-search/github.svg)](https://agentmods.dev/skills/ogulcancelik/agent-skills/web-search)

Your own site

<a href="https://agentmods.dev/skills/ogulcancelik/agent-skills/web-search"><img src="https://agentmods.dev/badge/skills/ogulcancelik/agent-skills/web-search/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ogulcancelik/agent-skills/web-search"><img src="https://agentmods.dev/badge/skills/ogulcancelik/agent-skills/web-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 647 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00068	$0.00647
Opus 5.5	$0.00027	$0.00259
Sonnet 5.5	$0.00014	$0.00129
Haiku 4.5	$0.00007	$0.00065

Measured 14d ago against content hash c6c6717d0032, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

web-search scanned grade A with 1 finding 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 14d ago.

The scan reads SKILL.md. This mod also ships 21 executable files (lib/bot-protection.js, lib/browser-bin.js, lib/cdp.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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Search the internet with Google or DuckDuckGo, inspect results, and extract selected pages as readable Markdown. Use when answers require current web sources, JavaScript-rendered pages, or browser access tha

skills/web-search/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Search

Use the bundled CLI to search through a local browser, visit results, and extract pages as clean Markdown for agent context. The persistent browser daemon reduces bot-detection failures and avoids repeated browser startup costs.

The entry point is {baseDir}/web-search.js, where {baseDir} is the absolute directory containing this SKILL.md. Always invoke that absolute path. Never run ./web-search.js from the caller's project directory.

Setup

If dependencies are missing, run bun install in the skill directory.

The CLI auto-detects Chromium-family browsers. Override detection with WEB_SEARCH_BROWSER_BIN or --browser-bin <path>.

Search and fetch

{baseDir}/web-search.js "query"
{baseDir}/web-search.js "query" -n 10
{baseDir}/web-search.js --from <result-set-id> --fetch 1,3,5
{baseDir}/web-search.js --url https://example.com
{baseDir}/web-search.js --url https://example.com --full

Each search prints a result-set ID. Always pass that ID with --from when fetching numbered results; result sets expire after ten minutes. Use --full only when the complete page text is needed.

Browser daemon

Direct calls use a local daemon by default for a warm browser session.

{baseDir}/web-search.js --daemon status
{baseDir}/web-search.js --daemon start
{baseDir}/web-search.js --daemon stop
{baseDir}/web-search.js --daemon restart
{baseDir}/web-search.js --no-daemon --url https://example.com

Troubleshooting

Treat one blocked page as a normal site-specific failure. Retry once, use another result, or try the direct URL before changing browser state.

For repeated timeouts, daemon errors, or blocks across multiple attempts:

Check {baseDir}/web-search.js --daemon status.
Run {baseDir}/web-search.js --daemon restart and retry.
If blocks persist, inspect health.profileDir in the status output. Stop the daemon, delete only that hidden skill profile directory, then start the daemon again. This resets stale cookies and browser storage without touching the user's normal browser profile.

Read the full file on GitHub · 61 lines

Files

What ships with it

25 files 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.

14d ago Changed c6c6717d0032
2mo ago First seen · 61 lines · 68 tokens per session scan A fc1a114e030e

Subscribe to this mod's changes

web-search is a skill published in the GitHub repository ogulcancelik/agent-skills (80 stars, last pushed 14d ago), licensed MIT. It adds 68 tokens to every session and 647 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automation Research

web-search next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
web-searchogulcancelik/agent-skills	Skill	80	14d ago	MIT	A	68	Claude Code, Codex
interactive-loginyc-software/qm	Skill	16k	yesterday	MIT	A	46	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	43	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	3d ago	MIT	A	68	Claude Code, Codex
open-design-browsercompozy/compozy	Skill	2.8k	yesterday	MIT	A	56	Claude Code, Codex
southwestborski/travel-hacking-toolkit	Skill	895	yesterday	MIT	A	40	Claude Code

web-search