The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts using the Bash tool to perform validation. It runs project-level hooks located in $CLAUDE_PROJECT_DIR/.claude/hooks/validators/ via uv run and its own internal validation script scripts/validate_review.py. These executions are limited to local scripts within the project environment.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection attack surface as a byproduct of its primary function.
Ingestion points: The skill reads content from plan.md and phase files (e.g., phase-NN-*.md) within the targeted plan folder.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present for the target file content.
Capability inventory: The skill utilizes Write, Edit, Bash, TaskCreate, and TaskUpdate tools to modify files and manage the project state.
Sanitization: No explicit sanitization or filtering is performed on the content read from the project files being reviewed.

review-plan