The Agent Skills Directory

[SAFE]: The skill implements a purely logic-based workflow for retrospective analysis. All file operations are restricted to a local artifact directory (.agents/postmortem/). The validation script scripts/validate.sh is a benign linter that ensures the skill's instructions remain consistent with its stated constraints (e.g., ensuring it does not attempt to perform forbidden actions like git commits or tracker updates). No network requests, sensitive file access, or remote code execution patterns were detected.

postmortem