Results for “worktree”

Mandatory rules for agents in git worktree isolation.

The English summary is being prepared. Showing the original description.

Set up isolated git worktrees. Use when starting isolated work, or when ce-work/ce-code-review offers a worktree option; detect existing isolation first.

The English summary is being prepared. Showing the original description.

Executes a groomed milestone with parallel kage-bunshin sessions in isolated worktrees. Use when a milestone has been groomed and /groom-milestone has produced a dispatch plan. Reads the dispatch plan, creates an integration branch, spawns one kage-bunshin (independent claude -p process) per wave item in its own worktree — each session is a full orchestrator with the Agent tool. Sequentially merges worktree branches, relays wave discoveries to subsequent waves, then lands the integration branch to main. Takes a milestone number as argument.

The English summary is being prepared. Showing the original description.

Report which local git worktrees under tmp/ are safe to close, need a human look, or are explicitly protected. Use when the user says /fleet-audit, asks what worktrees can be cleaned up, or wants a status check across all Ralph-loop/spike worktrees before running closeout on any of them.

The English summary is being prepared. Showing the original description.

Git worktree management for working on multiple branches in parallel. Create, list, remove, and synchronize worktrees. Protects against direct pushes to master.

The English summary is being prepared. Showing the original description.

Coordinate safely with a peer interactive session sharing the same git worktree — check first whether a separate worktree removes the problem, then declare path and branch scope before the first edit, survive a contended index lock, and review the whole branch before opening a PR. Activate when starting work in a repository that may already be occupied, when a git command fails with `index.lock: File exists`, when `guard:snapshot` refuses because a snapshot already exists, or when a commit turns out to contain a file this session never edited. When one session leads and the other supports, divide the labour by shape and re-derive every reported number against a named revision before citing it. Distinct from subagent concurrency: a peer session cannot be bracketed, because no baseline exists from before its edits.

The English summary is being prepared. Showing the original description.

Meta-agent supervisor that manages a fleet of Claude Code agents running in tmux windows. Auto-discovers spare worktrees, spawns agents, monitors state, kicks idle agents, approves safe confirmations, and recycles worktrees when done. TRIGGER when user asks to supervise agents, run parallel tasks, manage worktrees, check agent status, or orchestrate parallel work.

The English summary is being prepared. Showing the original description.

Audits git repository hygiene: worktree state, stale branches, uncommitted changes, orphaned worktrees, and hook configuration. Finds the rot before it causes a crisis.

The English summary is being prepared. Showing the original description.

Use this skill whenever a task involves running parallel work on a git repository without conflicts — e.g. "fix this bug while I keep working on my feature", "run Claude on two branches at once", "work on this task in isolation", "create a throwaway branch for this experiment", or anything where two agents or sessions might edit the same files. Also trigger when the user asks to use worktrees directly, or when an agent needs its own isolated checkout so it can work without disturbing the main branch. Even if the user just says "do this in parallel" or "don't mess up my current work", consider worktrees.

The English summary is being prepared. Showing the original description.

Manages git worktrees for parallel agent isolation: creates parallel/{name}-{timestamp} branches, merges with conflict detection. NOT for user feature branches (use git worktree directly).

The English summary is being prepared. Showing the original description.

Set up parallel agent team for COMPLEX tasks. Creates worktree structure, generates ownership map, and initializes task queue. Use when orchestrator decomposes a task into parallel subtasks, or when asked to "set up team", "parallel setup", or "configure worktrees".

The English summary is being prepared. Showing the original description.

Implements one issue in its own git worktree (agent/issue-N): smallest correct change, self-check, commit, JSON report. Use when launched with AGENT_FLOW_ROLE=implementer or asked to implement a specific issue in a worktree.

The English summary is being prepared. Showing the original description.

Create isolated git worktrees with smart directory selection and safety verification

The English summary is being prepared. Showing the original description.

Git Worktree Runner (gtr) workflow guidance for parallel development with Claude Code. Use when the user asks about git worktrees, parallel AI development, running multiple Claude sessions, managing worktrees with gtr, or setting up isolated development environments for feature work.

The English summary is being prepared. Showing the original description.

Git worktree を使った並列開発時に使用。配置・ポート割当・環境コピー・クリーンアップを標準化する。

The English summary is being prepared. Showing the original description.

The standing order for local git state in every AI Matrx repo — zero worktrees, zero local branches, zero dirty files, zero open PRs, everything merged to origin/main, and no code ever lost. Use when you find a worktree, a local branch, a stale checkout, an unpushed commit, or a dirty tree in any repo under /Users/armanisadeghi/code, when asked to "clean up", "unify", "merge everything", or when you are tempted to create a worktree or branch. Works without any access to Arman.

The English summary is being prepared. Showing the original description.

Permanent-delete grooming for leftover Docker builds, agent worktrees, and .next caches. Use when creating or finishing a git worktree, after a local docker build, when the disk is full, or when /tmp or .wt trees were left behind.

The English summary is being prepared. Showing the original description.

Carry out an existing implementation plan in one session, task by task. Verify each step with tests, record progress and decisions in a file, and finish with a review of all changes on the branch.

• Implementing a prepared development plan
• Executing tasks without implementer subagents
• Resuming work from a progress record

Coordinate parallel AI agent sessions with dmux, a tool that manages terminal panes. Split development, research, testing, or review into separate tasks, isolate overlapping file changes, and review results before merging them.

• Running research and implementation in parallel
• Splitting database, API, and UI work across agents
• Coordinating test monitoring and fixes

Delegate feature development, code refactoring, and pull request reviews to OpenAI Codex CLI. The skill also covers monitoring long tasks and fixing multiple issues in parallel using separate Git working directories.

• Adding a feature to an existing project
• Refactoring an authentication module
• Reviewing proposed code changes

Guides delegation of coding tasks to Claude Code CLI through Hermes. Covers one-shot runs and ongoing interactive sessions for feature work, bug fixes, refactoring, and reviews, with controls for tool permissions, execution limits, and structured results.

• Delegating feature implementation or bug fixes
• Reviewing code changes and pull requests
• Iterating on refactoring and tests

Start and repair isolated Paperclip development workspaces through managed services. Restore a full database clone when needed, then verify login, populated data, health, service visibility, and whether the process using the port belongs to the intended workspace.

• Starting or restarting a managed development workspace
• Repairing setup, login, or missing cloned data
• Resolving port conflicts between workspaces

Prepare Paperclip changes for a pull request by organizing commits, updating the branch, writing the description, addressing automated review feedback, and checking tests and CI before reporting the result for handoff.

• Preparing completed Paperclip changes for review
• Resolving Greptile feedback and failed checks
• Splitting large changes into separate pull requests

Coordinate bounded test runs for one Terminal-Bench task through Paperclip. Record evidence, diagnose failures, and manage approval for product fixes while keeping reruns in the same isolated working copy.

• Repeating a single Terminal-Bench task within set limits
• Diagnosing why a benchmark run stopped
• Managing approval before product fixes