The Agent Skills Directory

[SAFE]: The skill serves as a development guide and template for building robust agent runtimes. It includes specific instructions to implement safety guards, including schema validation for model-produced inputs, permission checks for 'risky' tools (read/write/execute), and explicit exit conditions (max turns, timeouts, and budget limits).
[SAFE]: No evidence of prompt injection, data exfiltration, or malicious persistence mechanisms was found. The provided TypeScript template follows standard agentic patterns and promotes deterministic control flow and reliability.
[SAFE]: External references are limited to standard licensing (Apache 2.0) and architectural documentation. No suspicious remote code execution or obfuscation techniques were detected.

query-loop-implementation