Agent Skills › winstonkoh87/Athena-Public › git-worktree-swarm

git-worktree-swarm

GitHub

自动化并行Git工作树设置，支持多子代理同时开发。通过波次执行尊重依赖关系，结合上下文隔离与原子提交，实现无冲突协作及自动合并清理。

examples/skills/coding/git-worktree-swarm/SKILL.md winstonkoh87/Athena-Public

触发场景

swarm parallel agents setup worktrees multi-agent wave execution

安装

npx skills add winstonkoh87/Athena-Public --skill git-worktree-swarm -g -y

更多选项

非标准路径

npx skills add https://github.com/winstonkoh87/Athena-Public/tree/main/examples/skills/coding/git-worktree-swarm -g -y

不安装直接使用

npx skills use winstonkoh87/Athena-Public@git-worktree-swarm

指定 Agent (Claude Code)

npx skills add winstonkoh87/Athena-Public --skill git-worktree-swarm -a claude-code -g -y

安装 repo 全部 skill

npx skills add winstonkoh87/Athena-Public --all -g -y

预览 repo 内 skill

npx skills add winstonkoh87/Athena-Public --list

SKILL.md

Frontmatter

{
    "name": "git-worktree-swarm",
    "model": "default",
    "auto-invoke": false,
    "description": "Automates the complex setup of parallel git worktrees for agentic swarms with dependency-aware wave execution.",
    "allowed-tools": [
        "Bash"
    ],
    "argument-hint": "deploy <agents> | cleanup | waves",
    "context_trigger": "worktree, parallel agents, swarm, multi-agent, concurrent development, wave execution"
}

Git Worktree Swarm Orchestrator

Sets up parallel, isolated git environments so multiple sub-agents can work on the same repository simultaneously without merge conflicts. Uses wave-based execution to respect task dependencies.

Triggers

"swarm", "parallel agents", "setup worktrees", "multi-agent", "wave execution"

Core Mechanics

Phase 1: Setup

Detect current branch.
Spawn n temporary worktrees (.agent-workspace-1, etc.).
Assign tasks to isolated clones.

Phase 2: Wave Execution (Dependency DAG)

Plans are grouped into waves based on dependency analysis:

WAVE 1 (parallel — no dependencies)
├── Worktree A: Task 1 (User model)     → Fresh context (P513)
├── Worktree B: Task 2 (Product model)  → Fresh context (P513)
│
[State merge: A.state + B.state → combined handoff]
│
WAVE 2 (parallel — depends on Wave 1)
├── Worktree C: Task 3 (Orders API, needs User model)
├── Worktree D: Task 4 (Cart API, needs Product model)
│
[State merge: C.state + D.state → combined handoff]
│
WAVE 3 (sequential — depends on Wave 2)
└── Worktree E: Task 5 (Checkout UI, needs Orders + Cart)

Wave Assignment Rules:

Condition	Assignment
Task has no dependencies	Wave 1
Task depends on Wave N output	Wave N+1
Tasks touch the same files	Same wave, sequential (not parallel)
Task has cross-cutting concerns	Latest wave of any dependency

Phase 3: Context Isolation (P513)

Each worktree agent receives only:

The specific plan/task
Relevant source files (from dependency analysis)
STATE.md (accumulated decisions from prior waves)
Project context (design.md / REQUIREMENTS.md)

Never: full conversation history, debug logs, unrelated research.

Phase 4: Merge

Each task commits atomically (P43 micro-commit).
Merge worktrees back to main branch in wave order.
Conflict resolution: if merge conflicts arise, spawn resolution agent.
Cleanup: remove temporary worktrees.

Reference Paths

Protocol 513: Context Isolation
Protocol 43: Micro-Commit
.context/memories/protocols/engineering/100-git-worktree-parallelism.md
.context/memories/protocols/architecture/409-parallel-worktree-orchestration.md