The parallel-work protocol — drive one topic on its own git worktree as review-gated slices, landing only on the human's OK; plus relay, the pair-programming-by-worktree primary that turns your comments into worktree sub chats. Pairs with worktree-guards.
Plugin worktree from marketplace optimiziramsi in optimiziramsi/skills. Commands read from the repo's manifest — yesterday.
relayPair-programming by worktree — the human edits and leaves comments in ONE shared worktree; this chat is the PRIMARY that turns those comments into topics, spawns one `worktree`-skill sub chat per topic (fresh session, own worktree cut off the integration branch), rebases the shared branch after ever
worktreeDrive a worktree topic — parallel, isolated work in a dedicated git worktree that lands into the integration branch only on the human's explicit OK. Invoke as `/worktree ...`, or when this chat is doing worktree work: "let's worktree this", "new worktree for X", "do this on a worktree", "you're work
/worktree:relayPair-program by worktree — this chat orchestrates: turns your comments in the shared worktree into topics, spawns one worktree sub chat per topic, rebases, strips, closes (runs the relay skill)
/worktree:worktreeDrive a parallel, isolated worktree topic — reserve, plan, execute reviewed slices, land to the integration branch (runs the worktree skill)
Keep the agent instruction system small and true — its rules (instructions-maintenance, rules-change), the instructions-audit sweep + auditor agent, and the caps / meta-lint size and structure checks.
3 skills · 3 commands · 1 agent · hooks
Structured review — the review skill (P0/HIGH/MED/LOW → .agent/reviews/) plus semantic-bug, spec, doc-drift, multi-tenant isolation and wireframe reviewer agents.
1 skill · 1 command · 5 agents
Unattended background work — looper / grind / collab prepare jobs that the shipped loop and grind runners execute as headless claude sessions, confined when run in a worktree.
3 skills · 3 commands · hooks
Session continuity — handoff (next-session notes, ≤4k), continue, session-summary, and a SessionStart state snapshot.
3 skills · 3 commands · hooks
The .todo parking lot — triage-todo, feedback and scope-cut, plus a guard that keeps .todo the user's (arm with "ALLOW TODO").
3 skills · 3 commands · hooks
Learn once, keep it — retro harvests a session's learnings, lessons curates them in .agent/lessons/, and the lesson-scout agent finds prior art before you re-debug.
2 skills · 2 commands · 1 agent
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.