Skip to content
Back to search

repobrain

SkillGitHubIncomplete

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/study8677/repobrain with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/study8677/repobrain'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/study8677--repobrain/badge.svg)](/listings/study8677--repobrain)

HTML

<a href="/listings/study8677--repobrain"><img src="/api/listings/study8677--repobrain/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Ask an AI assistant that can run commands in your project to install RepoBrain:

> Read [AI_INSTALL.md](https://github.com/study8677/repobrain/blob/main/AI_INSTALL.md) and follow it to install RepoBrain in this project.

The guide installs the tools, configures a model backend, then builds the knowledge base and checks an answer. A logged-in headless CLI such as Trae can serve as the backend without an API key; an OpenAI-compatible API is also supported. Requirements: Python 3.10+, Git with at least one commit, and a clean worktree before refresh.

For platform-specific installation or manual configuration, see [the installation guide](INSTALL.md) and [the quick-start guide](docs/en/QUICK_START.md). Installing RepoBrain into an existing project does not require `rb init` or `rb-init`.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 21 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "repobrain",
  3. "owner": {
  4. "name": "RepoBrain Team",
  5. "email": "fanjingwen50@gmail.com",
  6. "url": "https://github.com/study8677/repobrain"
  7. },
  8. "metadata": {
  9. "description": "RepoBrain developer tools for project knowledge refresh and routed codebase Q&A."
  10. },
  11. "plugins": [
  12. {
  13. "name": "repobrain",
  14. "source": "./",
  15. "description": "Repository knowledge engine: CLI-backed slash commands (rb-setup / rb-init / rb-refresh / rb-ask) for both Claude Code and Codex CLI, agent-repo-init skill, and optional MCP server.",
  16. "version": "0.4.0",
  17. "category": "developer-tools",
  18. "keywords": ["mcp", "knowledge-graph", "multi-agent", "scaffolding"]
  19. }
  20. ]
  21. }
README.md · README · 284 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. <img src="docs/assets/logo.svg" alt="RepoBrain" width="140"/>
  3. # RepoBrain
  4. Cross-IDE repository knowledge engine for grounded codebase Q&A.
  5. <sub>Formerly known as <b>Antigravity Workspace Template</b> — same project, new name.</sub>
  6. **English** · [中文](README_CN.md) · [Español](README_ES.md)
  7. [![License](https://img.shields.io/badge/License-MIT-22C55E?style=flat-square)](LICENSE)
  8. [![Python](https://img.shields.io/badge/Python-3.10+-3776AB?style=flat-square&logo=python&logoColor=white)](https://python.org/)
  9. [![CI](https://img.shields.io/github/actions/workflow/status/study8677/repobrain/test.yml?style=flat-square&label=CI)](https://github.com/study8677/repobrain/actions)
  10. [![DeepWiki](https://img.shields.io/badge/DeepWiki-Docs-3B82F6?style=flat-square&logo=gitbook&logoColor=white)](https://deepwiki.com/study8677/repobrain)
  11. [![NLPM](https://img.shields.io/badge/NLPM-audited-7C3AED?style=flat-square)](https://github.com/xiaolai/nlpm-for-claude)
  12. [![Stars](https://img.shields.io/github/stars/study8677/repobrain?style=flat-square&color=F59E0B)](https://github.com/study8677/repobrain/stargazers)
  13. <img src="docs/assets/demo.gif" alt="rb-ask demo — ask your codebase, get grounded answers with file paths and line numbers" width="800"/>
  14. </div>
  15. <div align="center">
  16. <p><strong>🚀 实测推荐:</strong> <a href="https://teamorouter.com/?i=e188641773">TeamoRouter</a> —— 非广告,我自己在 Codex、Claude Code 等 AI 编程工具里高强度使用:一个 API Key 接入 Claude、GPT-5.5 等,模型价格方便调整,价格优惠,并没有掺水的情况。接入指南见 <a href="https://github.com/xixiaoyao/openrouter-api-key">openrouter-api-key</a>。</p>
  17. </div>
  18. RepoBrain helps you understand an unfamiliar repository, trace an implementation,
  19. and ask questions with source-file references. It keeps project knowledge in
  20. `.repobrain/`, shared across supported IDEs and agents.
  21. ## Project Philosophy
  22. **Cross-IDE repository knowledge engine for grounded codebase Q&A.** Same `.repobrain/` knowledge layer reads in every IDE; one engine, every host.
  23. > An AI Agent's capability ceiling = **the quality of context it can read.**
  24. `rb-refresh` deploys a multi-agent cluster that autonomously reads your code — each module gets its own Agent that generates a knowledge doc. `rb-ask` routes questions to the right Agent, grounded in real code with file paths and line numbers.
  25. **Instead of handing Claude Code / Codex a repo-wide `grep` and making it hunt on its own, give it a ChatGPT for your repository.**
  26. ```
  27. Traditional approach: RepoBrain approach:
  28. CLAUDE.md = 5000 lines of docs Claude Code calls ask_project("how does auth work?")
  29. Agent reads it all, forgets most Router → ModuleAgent reads actual source, returns exact answer
  30. Hallucination rate stays high Grounded in real code, file paths, and git history
  31. ```
  32. <details>
  33. <summary><b>Four concrete failure modes RepoBrain fixes</b> — click to expand</summary>
  34. | Problem | Without RepoBrain | With RepoBrain |
  35. |:--------|:-------------------|:-----------------|
  36. | Agent forgets coding style | Repeats the same corrections | Reads `.repobrain/conventions.md` — gets it right the first time |
  37. | Onboarding a new codebase | Agent guesses at architecture | `rb-refresh` → ModuleAgents self-learn each module |
  38. | Switching between IDEs | Different rules everywhere | One `.repobrain/` folder — every IDE reads it |
  39. | Asking "how does X work?" | Agent reads random files | `ask_project` MCP → Router routes to the responsible ModuleAgent |
  40. Architecture is **files + a live Q&A engine**, not plugins. Portable across any IDE, any LLM, zero vendor lock-in.
  41. </details>
  42. Read the full [project philosophy](docs/en/PHILOSOPHY.md).
  43. ## Quick Start
  44. Ask an AI assistant that can run commands in your project to install RepoBrain:
  45. > Read [AI_INSTALL.md](https://github.com/study8677/repobrain/blob/main/AI_INSTALL.md) and follow it to install RepoBrain in this project.
  46. The guide installs the tools, configures a model backend, then builds the knowledge
  47. base and checks an answer. A logged-in headless CLI such as Trae can serve as the
  48. backend without an API key; an OpenAI-compatible API is also supported. Requirements:
  49. Python 3.10+, Git with at least one commit, and a clean worktree before refresh.
  50. For platform-specific installation or manual configuration, see
  51. [the installation guide](INSTALL.md) and [the quick-start guide](docs/en/QUICK_START.md).
  52. Installing RepoBrain into an existing project does not require `rb init` or `rb-init`.
  53. ## Everyday Use
  54. Run these commands in your project directory after installation and configuration:
  55. ```bash
  56. rb-refresh
  57. rb-ask "How does authentication work in this project?"
  58. ```
  59. `rb-refresh` automatically builds the first knowledge base, updates affected groups
  60. after committed changes, or continues a matching interrupted task. If knowledge is
  61. already current, it skips without calling a model. After a failure, run the same
  62. command again to continue.
  63. Use this only when you want to regenerate all knowledge:
  64. ```bash
  65. rb-refresh --full
  66. ```
  67. `rb-ask` reads the existing knowledge base and answers with source evidence. It
  68. reminds you when committed code is newer; it does not refresh during a question.
  69. Examples of useful questions:
  70. - Where is this API implemented, and what calls it?
  71. - How does data move from the UI to the backend?
  72. - Which modules are affected by changing this function?
  73. ## How It Works
  74. ```text
  75. Source code → rb-refresh → .repobrain/ knowledge → rb-ask → answer with code references
  76. ```
  77. RepoBrain groups related code, generates module knowledge, and routes each question
  78. to relevant context. Knowledge lives in your project, so supported IDEs share the
  79. same base. Updates are staged separately and become active only when complete;
  80. a failed update preserves the existing usable generation.
  81. The first build can take several minutes or longer on large repositories and
  82. uses your configured model. Commit or stash local changes before refreshing.
  83. IDE rules and new-project scaffolding are optional; see [the usage reference](docs/en/USAGE.md).
  84. ## Support Matrix
  85. | Use | Environments | How to connect |
  86. |:----|:-------------|:---------------|
  87. | Native plugins | Claude Code, Codex CLI | Setup, refresh, and ask via slash commands. |
  88. | Compatible IDEs | Cursor, Windsurf, Gemini CLI, VS Code + Copilot, Cline, Aider, DeepSeek Harness | Shared context files, CLI, or an MCP client. |
  89. | Other agents and scripts | Any host that can run commands or call MCP tools | CLI/JSON output or optional `rb-mcp`. |
  90. Platform-specific commands, JSON output, and MCP registration are documented in
  91. [the usage reference](docs/en/USAGE.md) and [INSTALL.md](INSTALL.md).
  92. ## Evaluation
  93. A locked comparison on Flask, ripgrep, Vite, and Prometheus used the same source
  94. access and model route for RepoBrain and CodeGraph + Trae. The
  95. [full report](benchmarks/codegraph-comparison/results/latest-v2-full-report.md)
  96. includes accuracy, query time, tokens, and cold-build cost. Results apply to that
  97. experiment; AI knowledge generation and static graph indexing are different workloads.
  98. ## Documentation
  99. - [Installation and troubleshooting](INSTALL.md)
  100. - [Commands, JSON, and optional integrations](docs/en/USAGE.md)
  101. - [Knowledge generation and Q&A architecture](docs/en/SWARM_PROTOCOL.md)
  102. - [External MCP tools](docs/en/MCP_INTEGRATION.md) · [Sandbox configuration](docs/en/SANDBOX.md)
  103. - [Release changes](CHANGELOG.md)
  104. - Full documentation: [English](docs/en/README.md) · [中文](docs/zh/README.md) · [Español](docs/es/README.md)
  105. **NLPM Audit Feedback** — Improved by [NLPM](https://github.com/xiaolai/nlpm-for-claude), a natural-language programming linter by [xiaolai](https://github.com/xiaolai).
  106. ---
  107. ## Contributing
  108. Ideas are contributions too! Open an [issue](https://github.com/study8677/repobrain/issues) to report bugs, suggest features, or propose architecture.
  109. ## Contributors
  110. <table>
  111. <tr>
  112. <td align="center" width="20%">
  113. <a href="https://github.com/Lling0000">
  114. <img src="https://github.com/Lling0000.png" width="80" /><br/>
  115. <b>⭐ Lling0000</b>
  116. </a><br/>
  117. <sub><b>Major Contributor</b> · Creative suggestions · Project administrator · Project ideation & feedback</sub>
  118. </td>
  119. <td align="center" width="20%">
  120. <a href="https://github.com/h13181278389">
  121. <img src="https://github.com/h13181278389.png" width="80" /><br/>
  122. <b>h13181278389</b>
  123. </a><br/>
  124. <sub><b>Core Contributor</b> · Thank you for your support, feedback, and contributions to RepoBrain</sub>
  125. </td>
  126. <td align="center" width="20%">
  127. <a href="https://github.com/flyw1015">
  128. <img src="https://github.com/flyw1015.png" width="80" /><br/>
  129. <b>flyw1015</b>
  130. </a><br/>
  131. <sub><b>Core Contributor</b> · Thank you for your support, feedback, and contributions to RepoBrain</sub>
  132. </td>
  133. <td align="center" width="20%">
  134. <a href="https://github.com/devalexanderdaza">
  135. <img src="https://github.com/devalexanderdaza.png" width="80" /><br/>
  136. <b>Alexander Daza</b>
  137. </a><br/>
  138. <sub>Sandbox MVP · OpenSpec workflows · Technical analysis docs · PHILOSOPHY</sub>
  139. </td>
  140. <td align="center" width="20%">
  141. <a href="https://github.com/chenyi">
  142. <img src="https://github.com/chenyi.png" width="80" /><br/>
  143. <b>Chen Yi</b>
  144. </a><br/>
  145. <sub>First CLI prototype · 753-line refactor · DummyClient extraction · Quick-start docs</sub>
  146. </td>
  147. </tr>
  148. <tr>
  149. <td align="center" width="20%">
  150. <a href="https://github.com/Subham-KRLX">
  151. <img src="https://github.com/Subham-KRLX.png" width="80" /><br/>
  152. <b>Subham Sangwan</b>
  153. </a><br/>
  154. <sub>Dynamic tool & context loading (#4) · Multi-agent swarm protocol (#3)</sub>
  155. </td>
  156. <td align="center" width="20%">
  157. <a href="https://github.com/shuofengzhang">
  158. <img src="https://github.com/shuofengzhang.png" width="80" /><br/>
  159. <b>shuofengzhang</b>
  160. </a><br/>
  161. <sub>Memory context window fix · MCP shutdown graceful handling (#28)</sub>
  162. </td>
  163. <td align="center" width="20%">
  164. <a href="https://github.com/goodmorning10">
  165. <img src="https://github.com/goodmorning10.png" width="80" /><br/>
  166. <b>goodmorning10</b>
  167. </a><br/>
  168. <sub>Enhanced <code>rb ask</code> context loading — added CONTEXT.md, AGENTS.md, and memory/*.md as context sources (#29)</sub>
  169. </td>
  170. <td align="center" width="20%">
  171. <a href="https://github.com/abhigyanpatwari">
  172. <img src="https://github.com/abhigyanpatwari.png" width="80" /><br/>
  173. <b>Abhigyan Patwari</b>
  174. </a><br/>
  175. <sub>Code knowledge graph integration for <code>rb ask</code> — symbol search, call graphs, and impact analysis</sub>
  176. </td>
  177. <td align="center" width="20%">
  178. <a href="https://github.com/BBear0115">
  179. <img src="https://github.com/BBear0115.png" width="80" /><br/>
  180. <b>BBear0115</b>
  181. </a><br/>
  182. <sub>Skill packaging & KG retrieval enhancements · Multi-language README sync (#30)</sub>
  183. </td>
  184. </tr>
  185. <tr>
  186. <td align="center" width="20%">
  187. <a href="https://github.com/SunkenCost">
  188. <img src="https://github.com/SunkenCost.png" width="80" /><br/>
  189. <b>SunkenCost</b>
  190. </a><br/>
  191. <sub><code>rb clean</code> command · <code>__main__</code> entry-point guard (#37)</sub>
  192. </td>
  193. <td align="center" width="20%">
  194. <a href="https://github.com/aravindhbalaji04">
  195. <img src="https://github.com/aravindhbalaji04.png" width="80" /><br/>
  196. <b>Aravindh Balaji</b>
  197. </a><br/>
  198. <sub>Unified instruction surface around <code>AGENTS.md</code> (#41)</sub>
  199. </td>
  200. </tr>
  201. <tr>
  202. <td align="center" width="20%">
  203. <a href="https://github.com/xiaolai">
  204. <img src="https://github.com/xiaolai.png" width="80" /><br/>
  205. <b>xiaolai</b>
  206. </a><br/>
  207. <sub><a href="https://github.com/xiaolai/nlpm-for-claude">NLPM</a> audit feedback · Skill frontmatter fixes · Dependency hygiene review (#51, #52, #53)</sub>
  208. </td>
  209. </tr>
  210. </table>
  211. ## Star History
  212. [![Star History Chart](https://api.star-history.com/svg?repos=study8677/repobrain&type=Date)](https://star-history.com/#study8677/repobrain&Date)
  213. ## License
  214. MIT License. See [LICENSE](LICENSE) for details.
  215. ---
  216. <div align="center">
  217. **[📚 Full Documentation →](docs/en/)**
  218. *Built for the AI-native development era*
  219. Friendly Link: [LINUX DO](https://linux.do/)
  220. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.