
Install groove's Claude Code native shell hooks into .claude/settings.json. Enables deterministic session-end reminders, git activity capture, automatic session-capture drafts, and managed-path protection.
Groove engineering workflow system. Top-level entry point. Use groove-daily-*, groove-work-*, groove-utilities-*, groove-admin-* for all workflow and admin commands.
Display all groove skills and commands with live config values.
Quantified compound-loop dashboard: lessons captured vs graduated, adherence streaks, and task velocity. Use to see whether the workflow is actually compounding.
Write the daily memory log entry. Use at end of day to record what happened.
Document lessons, update rules/templates/docs. Use to capture learnings after review.
Install a rich Claude Code statusline into ~/.claude/hooks/ and ~/.claude/settings.json. Displays model, git context, token usage, effort level, 5h/7d usage limits, and active /loop count with next-fire time.
Run all groove health checks: config, backends, companions, AGENTS.md.
Load groove workflow context into the conversation. Run at the start of every session.
Install groove's Cursor native hooks into .cursor/hooks.json. Enables compaction-safe re-priming, session-end reminders, git activity capture, automatic session-capture drafts, and managed-path protection.
Create or update .groove/index.md config interactively. Run before groove install.
Install groove backends, companions, and AGENTS.md bootstrap. Run once per repo.
Pull latest groove skills and apply pending migrations to local groove state.
End the workday: write memory, analyse tasks, run end hook. Use when wrapping up the day.
Start the workday: review yesterday, create today's daily memory, load tasks, prepare agenda. Use when beginning the day.
Publish a workflow learning to the groovebook shared commons as a GitHub PR. Use after groove-work-compound when a learning is worth sharing.
Check if a newer version of groove is available on GitHub.
Graduate a workflow insight from learned/<topic>.md into AGENTS.md as a permanent constraint. Use when a lesson is stable enough to apply to every future session.
Set up memory backend and configuration.
Roll up the weekly memory log from daily entries.
Create a new task in the configured backend.
Check task backend health and connectivity.
Log a workflow mistake, fix its root cause, and graduate the lesson to learned memory. Use when the agent makes an error you want to prevent recurring.
Create outcome spec (overview, decisions, steps, edge cases). Use $ARGUMENTS as spec topic if provided.
Capture and resolve deferred items from a session ('we'll come back to that'). Use $ARGUMENTS as the promise text, or --list / --resolve N.
Browse and review open learning PRs in the configured groovebook repo. Use to participate in the shared groove commons.
Analyse task status and distribution across the configured backend.
Archive a completed task in the configured backend.
Configure task backend settings interactively.
Set up task backend and configuration.
Analyse workflow trends: session ratings, recurring mistakes, and learnings over a period. Use for weekly or monthly reflection.
Execute the implementation plan, track progress in the task backend. Use after planning.
Roll up the monthly memory log from weekly entries.
Generate a GROOVE.md onboarding guide for contributors to a groove-enabled project. Explains the compound loop, commands, and conventions.
Check memory backend health and configuration.
Record git activity summary in memory log.
Review current branch for blindspots; fix now / needs spec / create issues.
List active tasks in the configured backend. Use to see current task status.
Update an existing task in the configured backend.
Clarify scope through dialogue, surface key decisions and open questions. Use before planning.
Create a 'how does X work' documentation file for a codebase component or concept. Use $ARGUMENTS as the doc topic if provided.
Research codebase, write concrete implementation plan. Use after brainstorming.
Evaluate output, identify lessons, decide accept/rework. Use after implementation.