3 tagged wishful programming, measured the same way as everything else here.
Hook Claude Code
Runs before the agent uses a tool for Bash, Write and Edit tool calls, executing hf.block-destructive-git.sh, hf.scan-secrets-before-commit.sh, hf.validate-tests-before-commit.sh, hf.validate-functional-areas.sh, hf.enforce-plan-and-explore.sh, hf.check-test-counterpart.sh, hf.enforce-migrations.sh and…
Hook Claude Code
Runs after a tool call finishes for Read, Grep, Glob, cclsp, TaskCreate, Write and Edit tool calls, executing hf.track-exploration.sh, hf.track-planning.sh, hf.warn-new-file-creation.sh, hf.track-code-changes.sh, hf.auto-lint-after-edit.sh and hf.mirror-feedback-memory.sh (11 commands). From T-rav/hydraflow.
Hook Claude Code
Runs when the agent finishes a response, executing hf.cleanup-code-change-marker.sh. From T-rav/hydraflow.