The Agent Skills Directory

[COMMAND_EXECUTION]: The references/system-assessment.md file includes scripts that execute git log and other shell commands via subprocess.run to identify codebase hotspots and hotspots. This is a standard architectural assessment practice and is well-documented within the skill's purpose.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted legacy codebases, creating an attack surface for instructions hidden in comments or data. However, the skill explicitly mandates characterization testing (safety nets) and human-in-the-loop validation checkpoints at every phase of the migration to mitigate these risks.
[SAFE]: All external references and methodologies (Strangler Fig, Branch by Abstraction) are standard industry best practices. The skill uses environment-based feature flags and provides robust rollback strategies, prioritizing production stability.

legacy-modernizer