web_searcher

web_searcher is an agent for Claude Code from inclusionAI/AWorld. It costs 30 tokens per session (328 once invoked), scanned A, original, MIT.

A web-research agent that finds technical documentation, recommended practices, and other relevant online resources, then combines the findings into a summary.

In plain words
What is it for?
Use it to research programming languages, libraries, frameworks, design patterns, common problems, and their solutions. It can read web pages and local reference files, but cannot edit files or run commands.
Why use it?
It reduces the time spent searching across websites and checking whether technical information is current and trustworthy.

Agent for Claude Code

Written for Claude Code: disallowed-tools in frontmatter.

About the project

AWorld is an agent harness, meaning a framework that coordinates an AI agent’s tools, memory, context, and execution so expert knowledge can be turned into reusable skills and autonomous agents. It is for building domain-specific agent applications and workflows, with the catalogue entries representing skills, agents, and commands that operate within the AWorld ecosystem.

inclusionAI/AWorld · 1,229 stars · on GitHub · aworldagents.com

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 agents/inclusionai/aworld/web_searcher
Clone the repo
git clone --depth 1 https://github.com/inclusionAI/AWorld

Made for: Claude Code.

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_searcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/inclusionai/aworld/web_searcher.svg)](https://agentmods.dev/agents/inclusionai/aworld/web_searcher)
Your own site
<a href="https://agentmods.dev/agents/inclusionai/aworld/web_searcher"><img src="https://agentmods.dev/badge/agents/inclusionai/aworld/web_searcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 328 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 $0.00030 $0.00328
Opus 5 $0.00015 $0.00164
Sonnet 5 $0.00006 $0.00066
Haiku 4.5 $0.00003 $0.00033

Measured 6d ago against content hash a23280ec2137, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

web_searcher 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.

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.

examples/subagent_integration/agents/web_searcher.md · 53 lines

What it actually says

Web Searcher Agent

Tools:

  • web_search: Search the web for information
  • web_fetch: Fetch and parse web pages
  • read_file: Read local reference files

Disallowed Tools:

  • write_file: Search-only mode
  • terminal: No command execution
  • cast_analysis: Focus on web search only

Configuration:

model: inherit
system_prompt: |
  You are a research specialist focused on finding and synthesizing technical information:
  - Official documentation (Python, JavaScript, frameworks)
  - Best practices and design patterns
  - Common pitfalls and solutions
  - Community discussions and expert opinions
  
  Research methodology:
  1. Start with official documentation sources
  2. Cross-reference with multiple authoritative sources
  3. Verify information currency (prefer recent sources)
  4. Synthesize findings into clear, actionable insights
  
  Output format:
  ## Sources Found
  - [Source 1]: [URL] - [Key points]
  - [Source 2]: [URL] - [Key points]
  
  ## Key Findings
  - [Synthesized insights from all sources]
  
  ## Recommendations
  - [Actionable recommendations based on 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. 6d ago First seen · 53 lines · 30 tokens per session scan A a23280ec2137

Subscribe to this mod's changes

web_searcher is an agent published in the GitHub repository inclusionAI/AWorld (1,229 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 328 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.

Related

Other agents, from other repositories

building-agents

Create intelligent agents that connect to MCP servers, discover tools automatically, and execute tasks with full observability.

promptise-com/Foundry · 0 tokens

reasoning-patterns

Every Promptise agent is powered by a Reasoning Graph. By default, buildagent() creates a ReAct graph (single node with tools) — and that default is smart by default: it manages context automatically (contextscope="auto"), so simple tasks are unchanged and deep tool loops stay token-efficient without you choosing…

promptise-com/Foundry · 0 tokens

cross-agent

Enable agents to delegate tasks to peer agents using auto-generated tools like askagentresearcher and broadcasttoagents.

promptise-com/Foundry · 0 tokens

server-specs

Configure how agents connect to MCP servers using StdioServerSpec for local servers and HTTPServerSpec for remote ones.

promptise-com/Foundry · 0 tokens

dashclaw-security-reviewer

Read-only security reviewer specialized for the DashClaw stack (Next.js 16 App Router, Neon/Postgres via repositories, API-key auth, x402 spend, webhooks, org/tenant scoping). Invoke before merging or shipping any diff that touches auth, API keys, x402/spend, webhooks, secrets/env, or database access. Reports findings…

ucsandman/DashClaw · 86 tokens

dashclaw-drift-auditor

Audits DashClaw's drift-prone hardcoded counts and version stamps — SDK method counts (Node/Python), MCP tool/resource counts, route counts, and the unified platform+SDK version — against the live source of truth, and reports every mismatch with file:line. Use before shipping, after route/SDK changes, or whenever…

ucsandman/DashClaw · 90 tokens