The easiest default
One Skills CLI command gives compatible agents Radar's workflow: start free, confirm paid scope and cost, cap spend, and report evidence and sampling limits.
npx skills add optifeed/optifeed-radar --skill optifeed-radar -gAgents / choose a surface
LET YOUR AGENT RUN THE RADAR.
Install the Radar skill for the quickest safe setup, use the Claude plugin for skill plus MCP in one package, or connect the local MCP server manually when you need structured tools.
THREE WAYS IN.
Five structured tools
Connect the local stdio server for structured tool calls, progress reporting, local snapshots, and default non-interactive cost caps.
See all five MCP tools →Commands and structured JSON
Run Radar directly from a shell or let an installed skill drive the CLI when MCP is not configured. The CLI supports audits, checks, reports, diffs, sources, and JSON output.
See CLI commands →TESTED GUIDES.
Install the skill globally
Use the Skills CLI once, then invoke $optifeed-radar or describe the audit you want. Add MCP later if you prefer structured tools.
Install skill plus MCP
Add Optifeed's public Claude marketplace and install the Radar plugin. It bundles the skill and starts the published MCP server.
Use Radar with Claude Code →START WITH FREE.
- Run the zero-key audit.
Use
audit yourbrand.comor ask the MCP server to callaudit_store. It checks crawler access, llms.txt, structured data, metadata, and the sitemap without calling an AI model. - Review the buyer questions.
Generate or export the prompt pack before a paid run so the category and intent are visible.
- Set a spend cap.
Visibility and shopping checks use your provider credit. Start with quick mode and an explicit
max_cost. - Inspect the evidence.
Treat scores as point-in-time estimates. Open the captured answers, positions, cited sources, and absences underneath the headline number.