3 tagged text to sql, measured the same way as everything else here.
Hook Claude Code
Runs before the agent uses a tool for mcp__snowflake-tools__(query_database, python_interpreter) and Write tool calls, executing require_writing.py and require_revision.py via python3 (2 commands). From StringNLPLAB/FlexSQL.
Hook Claude Code
Runs after a tool call finishes for Skill tool calls, executing mark_revision.py and mark_writing.py via python3 (2 commands). From StringNLPLAB/FlexSQL.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing guard-bun-test.sh via bash. From AtlasDevHQ/atlas.