The Agent Skills Directory

[SAFE]: The skill uses search utilities (rg, fd) to perform read-only analysis of local codebase manifests such as package.json, Dockerfile, and Kubernetes manifests to identify project topology.
[SAFE]: All file access is restricted to identifying architectural patterns such as API gateways, circuit breakers, and outboxes for assessment purposes.
[SAFE]: No network exfiltration, credential harvesting, or remote code execution patterns were detected within the skill's instructions or search patterns.
[SAFE]: The skill explicitly defines itself as a read-only advisor and includes logic to prevent over-engineering by recommending patterns only when specific triggers are identified in the codebase.

audit-backend-architecture