jigjoy-ai/baro

Name: jigjoy-ai/baro
Author: jigjoy-ai

Plugin插件 ⭐ 124 MIT Approval & Security审批与安全 Dev Workflow开发与代码工作流 Productivity & Tasks效率与任务

baro is an autonomous software factory. It compiles your goal into a machine-checkable contract, splits it into a DAG of stories, builds them in parallel across isolated git worktrees, and blocks every merge behind fail-closed gates — declared tests, build, an evidence critic, write-surface ownership. You review a PR the gates already accepted.

catalog descriptioncatalog 简介 / catalog description：A CLI that turns a goal into a pull request - and a sandbox for testing concurrent AI coding agents on the Mozaik runtime.

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

Baro is an autonomous software factory CLI that turns a user’s high-level development goal into a finished, verified pull request. It compiles the goal into machine-checkable contracts, splits the work into a DAG of incremental stories, and builds them in parallel across isolated git worktrees. All merges are blocked behind fail-closed gates including tests, builds, an evidence critic, and write ownership checks, so you only need to review a pre-verified PR. You install it via npm with npm install -g baro-ai, and it supports multiple LLM backends and multiple AI coding agents including DSH and Claude Code.

The standard interactive workflow for baro is straightforward: you navigate to your local git repository, run baro "your development goal" to launch the interactive TUI, and confirm the generated plan before baro starts executing tasks automatically. You can also run baro in headless detached mode for CI or automation, which returns a run ID immediately so you can check on progress or stop the run later from any device. This tool is ideal for developers working on large feature requests who want to offload the bulk of the implementation work to an autonomous agent. It also integrates smoothly into existing AI coding agent workflows for users of DSH, Claude Code, and other platforms.

Baro is released under the permissive MIT open source license, so you can use it for personal or commercial projects for free. To run baro locally, you need Node.js 20 or newer, a working git installation, and at least one configured LLM backend such as Claude CLI, Codex, or any OpenAI-compatible endpoint. You can run baro --doctor to automatically check your setup for any missing dependencies or configuration issues. If you don’t have a local LLM subscription or available hardware, you can also use baro’s cloud hosted service with pre-provisioned isolated sandboxes.

baro 是一款独立的自动化软件开发 CLI 工具，可将用户提出的开发目标转换为可机器校验的开发契约，拆分为有向无环图结构的开发任务，并行在隔离的 git 工作树中完成开发，所有合并都需要通过预设的测试、构建、代码审查等校验关卡，最终生成可审核的合并请求。它支持多种 LLM 后端，可集成 DSH、Claude Code 等多个 AI 编码代理平台。

典型工作流为用户进入本地项目仓库后，输入开发目标即可启动工具，工具会打开终端用户界面引导用户确认开发计划，之后自动执行所有拆分后的开发任务。用户也可以配置无头后台运行，随时查看运行状态、停止任务或恢复中断的运行。适合需要处理大型开发任务、希望将部分重复开发工作自动化的开发人员使用。

baro 采用 MIT 许可证开源，安装方式为通过 npm 全局安装，需要 Node.js 20 以上版本、git 环境，以及至少一个可用的 LLM 后端。用户可以通过 baro --doctor 命令检查本地环境配置。工具也提供云端运行选项，没有本地环境的用户可以直接使用云端沙箱运行任务。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：baro（jigjoy-ai/baro）
仓库：https://github.com/jigjoy-ai/baro
本站详情页：https://www.yhbd.top/plugins/jigjoy-ai-baro/
本站登记：类型 plugin · 归类 多平台兼容工具（非 DSH 原生） · 许可证 MIT · ⭐ 124 · 最近提交 2026-10-02 · 主语言 TypeScript · 未检测到 DSH 插件清单

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

No DSH plugin manifest detected - it may only carry the dsh-plugin topic, so the install method must be confirmed on the spot未检测到 DSH 插件清单：可能只是打了 dsh-plugin 话题，安装方式要现场确认
Not DSH-native: a multi-platform tool that may require Node / Electron or another runtime first非 DSH 原生，是多平台兼容工具：可能要先装 Node / Electron 等运行时

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add github:jigjoy-ai/baro

把 jigjoy-ai/baro 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

5.8 KB · 缓存于 2026-09-17 19:38:14 · 5.8 KB

baro

Type a goal in your repo. Walk away. Come back to a verified pull request.

One prompt → a 33-story plan → 808 passing tests → a PR, in 71 minutes. See a real run.

Install

npm install -g baro-ai

Needs Node 20+, git, and at least one backend: the claude CLI (default), codex, or any OpenAI-compatible endpoint. baro --doctor checks your setup.

Use

cd your-repo
baro "Add JWT authentication with role-based access control"

That opens the TUI: intake asks only what matters, you confirm the plan, the fleet runs.

For automation, detach and follow from anywhere:

baro --headless --detach --goal-file goal.txt   # prints a run id, returns immediately
baro watch <run-id>                             # follow milestone events
baro logs <run-id> --follow                     # tail the raw log
baro runs                                       # list live runs
baro stop <run-id>                              # stop one

Commands

Command	What it does
`baro "<goal>"`	run a goal in the current repo (TUI)
`baro --goal-file <path>`	read the goal from a file
`baro --headless --detach ...`	background run for CI/automation; prints the run id
`baro watch <run-id>`	follow a live run's milestones
`baro logs <run-id> [--follow]`	print or tail a run's log
`baro runs` / `baro stop <id>`	list / stop live runs
`baro --resume`	resume an interrupted run from `prd.json` — never re-plans
`baro --continue`	follow-up on the current branch — always re-plans
`baro --doctor`	self-diagnostic: backends, auth, gh, permissions
`baro login`	browser sign-in for baro cloud
`baro connect [--install-service]`	attach this machine as a cloud runner

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 jigjoy-ai/baro 的 README.md。在 GitHub 查看原文 →