Loading npm security reports…
Portable headless coding-agent runner — polls CognitionDesk for pending claude_code-target loops and executes them via pluggable engines (claude-cli today; agent-sdk later). Extracted and generalized from mcp-mounaji-rag's loop-runner.ts.
Static analysis completed at 65.0% confidence. No malicious behavior was detected; 4 low-signal pattern(s) were surfaced and cleared.