By jacobcy
Orchestrate coding sessions with automated flow management, branch/PR workflows, code reviews, project governance, and skill configuration for the Vibe Coding Control Center.
Use for deep inspection of single flow when automated processes fail. Human intervention for complex flow/task binding issues, runtime state inconsistencies, and manual diagnosis. Do not use for routine monitoring (use vibe3 task status) or system-level debugging (use vibe-debug-serve).
Use when manager has signaled flow terminal state cleanup via handoff indicate. Reads cleanup instructions and executes FlowCleanupService. Do not use for code changes or PR creation.
Use when the user wants to classify dirty changes, create serial commits, split work into one PR or multiple PRs, and prepare publication from the correct flow without handling merge or post-merge closure.
Use when the user wants to resume work on an existing branch or flow. Reads context, executes the next step, reviews the result, and reports to the user before proceeding. Equivalent to superpowers:executing-plans, using vibe3 as the execution backend.
Use when checking orchestra service health, viewing serve running status, debugging vibe3 serve (orchestra server), checking whether a new serve debugging round is ready, inspecting agent execution logs in temp/logs/, diagnosing governance or manager chain failures, or identifying bugs in the heartbeat/dispatch pipeline. Triggered by "serve status", "orchestra service running", "FailedGate", "heartbeat", "serve health". Do not use for flow/task metadata repair (use vibe-check) or issue pool governance (use vibe-orchestra).
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Vibe Center 3.0 的主系统是 V3 Python 运行时。V2 Shell 仍保留环境工具和兼容能力,但不再是默认的语义中心。项目目标不是替代 git 和 gh,而是把本地 execution scene、agent handoff、runtime observation 和 skill governance 收敛到一套清晰边界里。
git 负责 branch 生命周期gh 负责 issue / PR 的常规远端操作vibe3 负责本地 flow scene、issue 绑定、handoff、runtime observationskills/ 与 workflows 负责编排,不负责重新发明共享状态模型一句话:模块给能力,agent / skill 做判断。
V2 保留环境工具和基础 shell 能力:
vibe toolvibe checkvibe keyswtnew 等 worktree / alias 辅助能力V3 是当前的本地运行时与协作主系统,核心能力包括:
vibe3 task status — 全局任务面板与 Flow 状态总览 (推荐,包含 assignee issue 总览)vibe3 status — [Compatibility] 全局状态兼容入口vibe3 flow show / rebuild / bind — Flow 现场管理vibe3 task show / intake / resume — 任务生命周期管理vibe3 handoff show / status / append — Agent 协作上下文vibe3 plan / run / review — Agent 执行入口vibe3 serve / scan / check — 基础设施与治理服务vibe3 snapshot / inspect / ask — 项目分析与知识检索# 1. 查看 V3 运行时与任务状态 (这是 Agent 的首选入口)
vibe3 task status # 全局任务面板(推荐,覆盖 Tier 3/2 概览)
vibe3 snapshot show # 查看项目健康度仪表盘 (Tier 1)
vibe3 flow show # 查看当前分支 Flow 详情 (Tier 2)
vibe3 internal bootstrap
zsh scripts/install.sh && source ~/.zshrc
/vibe-onboard
uv run python src/vibe3/cli.py status --verbose vibe keys check # (需 source ~/.zshrc)
/vibe-skills-manager
说明:
- `vibe3 task status` 是 V3 时代的首选看板,它聚合了跨 worktree 的任务事实。
- `vibe3 internal bootstrap` 负责当前项目 / worktree 的初始化(第三方 skills、OpenSpec、symlink、hooks、任务迁移等),可重复执行。
- `scripts/install.sh` 负责全局安装与命令可用性。
- `vibe doctor` 负责工具与 Claude plugins 的事实检查。
- `vibe keys check` 负责认证 / key 来源检查
- `/vibe-onboard` 负责引导用户检查和配置工具、Claude plugins、keys,并介绍项目与下一步
- `vibe skills check` / `/vibe-skills-manager` 负责把 skills 体系梳理清楚,避免 codeagent-wrapper 缺少必要能力
- `~/.vibe/keys.env` 由 `config/keys.template.env` 初始化而来,按需手动编辑
- 如果在安装、初始化或使用过程中遇到任何问题,欢迎向项目开发者提交 GitHub issue 说明现场与复现步骤
- skills 体系建议:
- Superpowers:Claude 用官方 plugin;其他 agent 用 `npx skills`
- OpenSpec:项目内初始化,按需启用
- Gstack:用户可选增强,建议全局安装到 `~/.claude/skills/gstack`
## Skills 入门
当 `/vibe-onboard` 和 `/vibe-skills-manager` 帮你把环境与能力体系梳理清楚后,可以从这些入口开始理解 skills:
- Superpowers
- `/brainstorming`
- Gstack(可选增强)
- `/office-hours`
- OpenSpec(项目内工具链)
- `/openspec-onboard`
## 推荐工作方式
```bash
# 新分支
git checkout -b feature/example
# 注册当前现场
uv run python src/vibe3/cli.py flow update
# 绑定 GitHub issue
uv run python src/vibe3/cli.py flow bind 123
# 查看当前现场
uv run python src/vibe3/cli.py flow show
# 执行 agent
uv run python src/vibe3/cli.py run --skill vibe-manager --async
Execution Level: L1 / L2
SOUL.md, CLAUDE.md, STRUCTURE.mdsupervisor/docs/standards/.agent/这一层定义宪法原则、规则、术语、流程边界和治理原则。核心动作包括 serve, scan, check。
Execution Level: L3
skills/.agent/workflows/src/vibe3/orchestra/, src/vibe3/agents/这一层负责理解上下文、决定下一步、编排能力调用顺序与上下文交换。核心动作包括 flow, task, run, plan, review。
Execution Level: L3 / L4
src/vibe3/ (commands, models, services, clients)bin/, lib/, config/lib3/ (V3 Hub)这一层只提供原子能力与状态读写,不负责隐藏 workflow 或进行重型决策。核心动作包括 handoff, inspect, pr, snapshot, ask。
agents/: plan / run / review agent pipelineanalysis/: symbol、snapshot、change scopeclients/: 外部系统客户端(Git, GitHub, SQLite, Serena 等)commands/: CLI 子命令config/: 配置加载、Profile 管理与 Pydantic schema 验证domain/: 领域事件与 handlers(events, handlers, orchestration_facade)environment/: 环境资源管理(Session 和 Worktree 统一抽象层)execution/: 执行控制平面(统一协调层:coordinator, capacity, lifecycle, gates)exceptions/: 统一异常层级models/: 领域数据模型(Flow, Handoff, Task, PR, Verdict 等 Pydantic 模型)observability/: 日志、链路追踪、审计orchestra/: 多 GitHub issue / 多 flow 的事实观察、排队与调度入口prompts/: prompt 组装与 provenanceroles/: 角色定义和执行模块(manager, plan, run, review, supervisor, governance)runtime/: heartbeat、event bus、executorserver/: webhook、MCP、health checkservices/: flow / PR / task / handoff 业务服务ui/: Rich 输出utils/: 通用工具函数(Git 辅助、分支工具、评论处理等)state/* label 只反映 flow 实际状态,不做主驱动flow_state.manager_session_id 等字段已 deprecated,只做兼容 fallback。npx claudepluginhub jacobcy/vibe-coding-control-centerAccess thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Next.js development expertise with skills for App Router, Server Components, Route Handlers, Server Actions, and authentication patterns