web-search

web-search is a skill for Claude Code, Codex from aws-samples/sample-strands-agent-with-agentcore. It costs 21 tokens per session (467 once invoked), scanned A, original, MIT.

A web search and page-reading service for finding current information, news, and research. It can search DuckDuckGo and extract readable text from web pages.

In plain words
What is it for?
Use it to search for specific topics, retrieve a small set of relevant links, and fetch the text of a chosen web page.
Why use it?
It saves time by finding targeted results and removing navigation and other page clutter when reading a source.

Skill for Claude CodeCodex

About the project

Sample Strands Agent with Amazon Bedrock AgentCore is an end-to-end reference architecture for building multi-agent chatbots on AWS. Teams use it to explore agent orchestration, tool execution, memory, browser automation, and agent-to-agent collaboration with Strands Agents and Bedrock AgentCore.

aws-samples/sample-strands-agent-with-agentcore · 192 stars · on GitHub

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/aws-samples/sample-strands-agent-with-agentcore/web-search
Any agent
npx skills add aws-samples/sample-strands-agent-with-agentcore --skill web-search
Clone the repo
git clone --depth 1 https://github.com/aws-samples/sample-strands-agent-with-agentcore

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-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/aws-samples/sample-strands-agent-with-agentcore/web-search.svg)](https://agentmods.dev/skills/aws-samples/sample-strands-agent-with-agentcore/web-search)
Your own site
<a href="https://agentmods.dev/skills/aws-samples/sample-strands-agent-with-agentcore/web-search"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-strands-agent-with-agentcore/web-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 467 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 $0.00021 $0.00467
Opus 5 $0.00010 $0.00234
Sonnet 5 $0.00004 $0.00093
Haiku 4.5 $0.00002 $0.00047

Measured 5d ago against content hash 49f6da8a3d2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-search 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 5d 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.

chatbot-app/agentcore/skills/web-search/SKILL.md · 50 lines

What it actually says

Available Tools

  • ddg_web_search(query, max_results=5): Search DuckDuckGo and return results with title, snippet, and link.
  • fetch_url_content(url, include_html=False, max_length=50000): Fetch a URL and extract clean text content.

Parameters

ddg_web_search

Parameter Type Default Description
query str (required) Search query string
max_results int 5 Number of results (max 10)

fetch_url_content

Parameter Type Default Description
url str (required) URL to fetch (must start with http:// or https://)
include_html bool False Include raw HTML in response
max_length int 50000 Maximum character length of extracted text

Usage Guidelines

  • Use specific, targeted search queries for best results
  • Set max_results to 3-5 for focused searches, up to 10 for broad research
  • Use fetch_url_content to read full page content from search result links
  • Break complex research into multiple targeted queries rather than one broad query
  • fetch_url_content automatically strips navigation, scripts, and boilerplate HTML
  • Reduce max_length for quick summaries or when you only need the beginning of a page

Citation Format

When presenting information from search results or fetched pages, wrap every specific claim in <cite> tags:

<cite source="SOURCE_TITLE" url="URL">claim text</cite>

Rules:

  • Cite factual claims, statistics, quotes, and specific information from search results.
  • The source attribute should contain the title or name of the source.
  • The url attribute should contain the source URL when available.
  • Do NOT cite your own reasoning or general knowledge.
  • If search results don't contain relevant information, inform the user rather than guessing.
  • Use the minimum number of citations necessary to support claims.
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. 5d ago First seen · 50 lines · 21 tokens per session scan A 49f6da8a3d2a

Subscribe to this mod's changes

web-search is a skill published in the GitHub repository aws-samples/sample-strands-agent-with-agentcore (192 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 467 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.

Related

Other skills, from other repositories

draw-image

Generate an image from a text prompt using an OpenAI-compatible image generation API (gpt-image-1-mini or compatible). The image is uploaded to the gofile.io public file sharing service and ONLY the public download page URL is returned. Trigger when user asks to draw, paint, generate, or create an image.

ai-sns/ai-sns · 67 tokens

A2A JSON-RPC Call

Call a peer agent's A2A JSON-RPC endpoint. Supports tasks/send (send a task message) and tasks/get (query task status).

ai-sns/ai-sns · 38 tokens

Fetch Agent Card

Fetch an A2A agent card JSON from a given endpoint URL. Tries direct GET first, then falls back to /.well-known/agent.json.

ai-sns/ai-sns · 35 tokens

Echo Skill Sample

Echo input parameters as JSON.

ai-sns/ai-sns · 10 tokens

mk:agent-browser

Browser automation CLI for AI agents using agent-browser. Use for navigating websites, clicking/filling pages, screenshots, data extraction, web app testing, exploratory QA, dogfooding, Electron apps, Slack automation, Vercel Sandbox browser runs, AWS AgentCore cloud browsers, auth-heavy flows, and long autonomous…

ngocsangyem/MeowKit · 114 tokens

health-event-impact-assessment

Evaluates AWS Health event impact on application workloads using topology knowledge. Determines blast radius, affected teams, and notification routing. Use this skill when investigating incidents triggered by AWS Health events including scheduled maintenance, operational issues, and service degradation notifications.

aws-samples/sample-aws-genai-ops-demos · 53 tokens