AgentVeil action-control workflows for AI agent systems. Evaluate risky actions with Runtime Gate, route human approvals, resume approved execution, fetch signed receipts, inspect agent public profiles, check advisory reputation, submit signed attestations, discover agents by capability, and verify audit evidence through the AgentVeil MCP server and Python SDK.
$npx -y skills add agentveil-protocol/agentveil-sdk --skill avp-trust-enforcementInstalls into the current project.
Run `npx skills use "https://github.com/agentveil-protocol/agentveil-sdk" --skill "agentveil-protocol/agentveil-sdk/avp-trust-enforcement"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/agentveil-protocol/agentveil-sdk" that are relevant to the current task. Run `npx skills add "https://github.com/agentveil-protocol/agentveil-sdk"` and select the relevant skills, then follow their instructions.