Web Recon — Development agent for Claude Code
Read-only web reconnaissance — fetch and report on documentation pages, changelogs, release notes; URL fact-checks with citations.
How to install Web Recon
Installs to ~/.claude/agents/crawford-young-claude-config-web-recon.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Crawford-Young/claude-config/HEAD/agents/web-recon.md -o ~/.claude/agents/crawford-young-claude-config-web-recon.md Restart Claude Code, or start a new session, for it to be picked up.
What Web Recon does
name: web-recon description: Read-only web reconnaissance — fetch and report on documentation pages, changelogs, release notes; URL fact-checks with citations. Dispatch for any question answerable by fetching a page, never for changing anything, and never for local-only questions (recon covers those). tools: Read, Grep, Glob, WebFetch, Agent model: haiku
You are a web reconnaissance agent. You look; you never change. You have no Bash, Write, or Edit access by design — do not attempt wor
Alternatives in Development
- Recon Ranker — Attack surface ranking agent 4.5k ★
- Herald — You are a specialized release agent 3.6k ★
- Network Recon Agent 261 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Manual Verifier
Independent fact-checker for answers built from the Ford service manual. Give it the vehicle, the question and
Source Explorer
Proactively use for a bounded read-only question answerable from current repository files, configuration, sche
Mp Explorer
Read-only reconnaissance for masterplan — run-bundle state reads, situation reports, and doctor-fact gathering
Jd Extractor
Fetch and normalize a job posting (URL or pasted text) into a structured JD brief. Use as the first stage of t
Orch Scout
Cheap-tier mechanical worker for the orchestrator. Use for Class: scan work — grep, glob, list, count, fetch a
Wiki Librarian
Specialized agent for searching, navigating, and answering questions from the knowledge base. Finds relevant p
Related Skills
MCP Web Scrape
🚀 mcp-web-scrape — Clean, cache-aware web content fetcher for AI agents. Fetch any URL → extract readable con
Google Docs
Answer a question from the local Google docs knowledge base (Search/SEO, Search Console, Ads, GA4) with citati
Qiaomu Markdown Proxy
Fetch any URL as clean Markdown via proxy services (r.jina.ai / defuddle.md) or built-in scripts. Works with l