pflow

End-of-session ritual for the pflow MAIN ORCHESTRATOR. Invoke when the user closes a session or the context window nears its end.

Boot the pflow MAIN ORCHESTRATOR — verify state, pick lane and work, launch and shepherd the agent hierarchy, merge, reconcile.

End-of-session ritual for the pflow MAIN ORCHESTRATOR. Invoke when the user closes a session or the context window nears its end.

Create task file from discussion context

Deploy specialized review agents to find bugs that general code review misses. Handles both plan review (before implementation) and code review (after implementation). Deploys 1-8 focused agents in capacity-aware parallel batches, scaled to plan/diff complexity, each targeting a specific blindspot category.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in context/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Run the pflow release process — generate changelog, bump version, commit, and create GitHub Release

Run focused tests and quality checks safely in the Codex sandbox for pflow or Loudkult. Use before testing either repository, especially when uv caches, home-directory writes, subprocess permissions, databases, Redis, or frontend tooling may behave differently inside the sandbox.

Screenshot or measure the running pflow web UI (the React Flow canvas; web/ → src/pflow/ui) to verify frontend changes. Use after changing web/ UI code.

This command is for human / machine invocation only. Do not use unless explicitly asked by the user.

Create a git worktree for a user driven agent.

Deploy specialized review agents to find bugs that general code review misses. Handles both plan review (before implementation) and code review (after implementation). Deploys 1-8 focused agents in capacity-aware parallel batches, scaled to plan/diff complexity, each targeting a specific blindspot category.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in context/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Author an implementation plan another AI agent can execute in isolation without ambiguity. Verifies assumptions against the codebase, weighs edge cases, and adds a light scope/model/agent nudge per phase. Use when turning an agreed design or task into an executable plan.

Author an implementation plan another AI agent can execute in isolation without ambiguity. Verifies assumptions against the codebase, weighs edge cases, and adds a light scope/model/agent nudge per phase. Use when turning an agreed design or task into an executable plan.

Read before updating CLAUDE.md files

This command is for human / machine invocation only. Do not use.

For initializing a manual verification process using an adversarial approach.

Ensure test pass the right thing

Run the pflow release process — generate changelog, bump version, commit, and create GitHub Release

Screenshot or measure the running pflow web UI (the React Flow canvas; web/ → src/pflow/ui) to verify frontend changes. Use after changing web/ UI code.