pw

Launch an agent team to collaboratively discuss, critique, and validate a specification before decomposing it into parallel-executable tasks.

Parse review feedback and spawn agent team for parallel fixes

Implement a task using an agent team in the current directory. No worktree creation, no automatic commits — the lead asks before shipping.

Create an isolated git worktree, then create an agent team to implement the task in parallel. Run autonomously through PR creation without requiring user approval.

Identify conflicting files and resolve in parallel via agent team

Spawn specialist reviewers for parallel critical PR review

$ARGUMENTS

$ARGUMENTS

Address review feedback and update the PR using parallel subagents for 3+ files

$ARGUMENTS

$ARGUMENTS

Pre-PR check for local verification, tests, code quality, and codebase consistency

Resolve merge conflicts with default branch using parallel subagents for 3+ files

Review a pull request critically for quality, security, and correctness

Check status of all parallel workers, PRs, and worktrees

Execute assigned task as a parallel worker following workspace rules

Clean up wt-j environments after PRs are merged

Execute a development task in a completely isolated git worktree environment.

Deep codebase analysis for understanding architecture, patterns, and complex dependencies. Use when thorough understanding is needed before major changes.

Fast codebase exploration for finding files, patterns, and code locations. Use for quick searches before implementation. Optimized for speed over thoroughness.

Lightweight implementation agent for small to medium code changes (under ~200 lines). Assesses task scope before implementation and rejects tasks that are too complex. Use for quick fixes, small features, and minor refactors.

Background status monitoring agent. Checks worker progress every 30 seconds and reports completion or errors. Designed to run in background while orchestrator continues other work.

Code quality standards for reviewing code changes. Activated when reviewing PRs, implementing features, or discussing code quality. Triggers on requests to "review code", "check quality", "improve code", or "refactor".

Reviews PR changes against the broader codebase to find inconsistencies, missed propagation, and stale references beyond the diff. Replicates senior reviewer codebase knowledge. Activates when reviewing PRs, checking consistency, or when changes touch shared entities across multiple files.

Security review checklist for code changes. Automatically activates when reviewing security-sensitive code, authentication, authorization, or data handling. Use when user asks to "check security", "review for vulnerabilities", "audit code", or when changes touch auth, crypto, user input, or API endpoints.

3 hooks across 3 events