AI上下文的ripgrep。在你的代理读取仓库之前，会有一张地图——并检查它写的内容。

排序确定性呼叫图：要触碰什么，破坏了什么，执行哪些测试。编辑：爆破 半径，达到它的测试，十二种质量类型只报告变差的部分，遗忘的共变，字段 读过和书写，名字有多种结局。

只是想用它？ 用下面的一句话安装它，然后每次编码会话开始时告诉你的代理： 比如说，用它：“在这个仓库上用ripwire。” 大多数人只需要这样：安装过程还能教你的代理 何时响应每个指令。

想要所有细节？ 底部的参考指南：安装、命令、输出 格式、退出代码和限制。你不需要这些来开始。

现场报告：是什么促成了大规模多代理编码合作——由Claude Fable 5.0编写，前沿模型在两天内协调了~20个编码代理，基于约1500个文件的C++/Metal代码库。点击查看完整报告。

对于单一开发者来说，这个工具是一个很好的查找加速器。对于编排车队，它就是负重的

Rip’n Fast. Fewer Tokens. Better Code.

The ripgrep of AI context. A map before your agent reads the repo — and a check on what it writes.

Ranked, deterministic call graph: what to touch, what it breaks, which tests to run. On the edit: blast radius, tests that reach it, twelve quality kinds reporting only what got worse, forgotten co-changes, fields read and written, names that resolve more than one way.

Just want to use it? Install it with the one line below, then start each coding session by telling your agent to use it, for example: “Use ripwire on this repo.” That is all most people need: the install also teaches your agent when to reach for each command.

Want every detail? The reference guide near the bottom covers install, commands, output format, exit codes and limits. You do not need it to get started.

For a single developer, this tool is a good lookup accelerator. For an orchestrated fleet, it’s load-bearing: it halved the research spend, twice redirected tasks before wasted work, prevented at least one silent-divergence shipped bug, and turned code-quality hygiene from a hope into a per-task mechanical gate. Whole-workflow ~2×; per-lookup 10–25×; and two moments where one call was worth more than the rest of the session’s tooling combined.

— the report’s bottom line

<img src=“docs/assets/field-report-multi-agent.jpg”