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.
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.
npx agentmods add agents/inclusionai/aworld/web_searchergit clone --depth 1 https://github.com/inclusionAI/AWorldWrote 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.
[](https://agentmods.dev/agents/inclusionai/aworld/web_searcher)<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>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 | $0.00030 | $0.00328 |
| Opus 5 | $0.00015 | $0.00164 |
| Sonnet 5 | $0.00006 | $0.00066 |
| Haiku 4.5 | $0.00003 | $0.00033 |
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.
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]
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.
- 6d ago First seen · 53 lines · 30 tokens per session scan A a23280ec2137
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.
Other agents, from other repositories
building-agents
Create intelligent agents that connect to MCP servers, discover tools automatically, and execute tasks with full observability.
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…
cross-agent
Enable agents to delegate tasks to peer agents using auto-generated tools like askagentresearcher and broadcasttoagents.
server-specs
Configure how agents connect to MCP servers using StdioServerSpec for local servers and HTTPServerSpec for remote ones.
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…
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…