[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-93004":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":15,"stars30d":13,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":16,"rankGlobal":10,"rankLanguage":10,"license":17,"archived":18,"fork":18,"defaultBranch":19,"hasWiki":18,"hasPages":20,"topics":21,"createdAt":10,"pushedAt":10,"updatedAt":42,"readmeContent":43,"aiSummary":44,"trendingCount":15,"starSnapshotCount":15,"syncStatus":14,"lastSyncTime":45,"discoverSource":46},93004,"lagune","wellwelwel\u002Flagune","wellwelwel","🌊 Lagune is your security copilot as you build, your Blue Team when you audit, whether you're a developer or not.","https:\u002F\u002Flagune.ai",null,"TypeScript",71,1,2,0,41,"MIT License",false,"main",true,[22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"agent-skills","ai","ai-driven","blue-team","claude-code","codex","copilot","cursor-ai","ia-driven","llm","prd","prompt-engineering","prompt-toolkit","sdd","sdh","security","security-driven-hardening","skills","spec-driven","spec-kit","2026-07-22 04:02:07","\u003Cimg src=\".\u002Fwebsite\u002Fstatic\u002Fimg\u002Fbanner.png\" \u002F>\n\n# 🌊 Lagune | [**lagune.ai**](https:\u002F\u002Flagune.ai)\n\n[![Version](https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002Flagune?label=&color=2f7bff&logo=npm&logoColor=white)](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Flagune)\n[![Docs](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocumentation-2f7bff?logo=docusaurus&logoColor=white)](https:\u002F\u002Flagune.ai\u002Fdocs)\n[![No API Key Needed](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNo%20API%20Key%20Needed-2f7bff?logo=claudecode&logoColor=white)](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fsupported-agents)\n\n**Lagune** helps your AI agent make a project more secure. You point it at your code, and the agent figures out what your system actually does, then guides you through the security work that matters for it.\n\n- **Lagune** works with projects in **any programming language** and supports [**37 agents**](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fsupported-agents) ✨\n\n---\n\nLove **Lagune**? [**Give us a ⭐ on GitHub**](https:\u002F\u002Fgithub.com\u002Fwellwelwel\u002Flagune)!\n\n---\n\n## Table of Contents\n\n- 🌊 [**Get Started**](#get-started)\n  - 📦 [**Dashboard**](#dashboard) | [**CLI**](#cli)\n  - 💬 [**Slash Commands**](#slash-commands)\n- 💽 [**Requirements**](#requirements)\n- 🔐 [**Security**](#security)\n- 🖖 [**Acknowledgements**](#acknowledgements)\n- 🧑‍⚖️ [**License**](#license)\n\n---\n\n## Get Started\n\n**Lagune** adapts to your environment, whether it is a new project or an existing one.\n\n> [!TIP]\n>\n> No API keys are needed, it runs directly through your own agent [(**Claude**, **Codex**, and more)](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fsupported-agents).\n\n---\n\n### Dashboard\n\nFor an interactive live view, follow-up, and maintenance, run:\n\n```bash\nnpx -y lagune@latest\n```\n\nIt serves a dashboard and opens it in a random port:\n\n- [x] **Live Reload**\n- [x] **Private** and **Local**\n- [x] **Install**, **Pull**, **Update**, and **Manage** all **Lagune** features directly from your browser\n- [x] No `node_modules` or `package.json` is needed 📦\n\n> \u003Cimg width=\"260\" src=\".\u002Fwebsite\u002Fstatic\u002Fimg\u002Fdashboard\u002F01.png\" \u002F>\n> \u003Cimg width=\"260\" src=\".\u002Fwebsite\u002Fstatic\u002Fimg\u002Fdashboard\u002F02.png\" \u002F>\n> \u003Cimg width=\"260\" src=\".\u002Fwebsite\u002Fstatic\u002Fimg\u002Fdashboard\u002F03.png\" \u002F>\n> \u003Cimg width=\"260\" src=\".\u002Fwebsite\u002Fstatic\u002Fimg\u002Fdashboard\u002F04.png\" \u002F>\n> \u003Cimg width=\"260\" src=\".\u002Fwebsite\u002Fstatic\u002Fimg\u002Fdashboard\u002F05.png\" \u002F>\n> \u003Cimg width=\"260\" src=\".\u002Fwebsite\u002Fstatic\u002Fimg\u002Fdashboard\u002F06.png\" \u002F>\n\n> [!TIP]\n>\n> - 🚪 Use `--port` or `-p` to specify a custom port.\n> - ⏏️ Press `Ctrl+C` to stop.\n\n---\n\n### CLI\n\n#### › Install\n\n```bash\nnpx -y lagune@latest init\n```\n\n- 🃏 **Lagune** runs on **Node.js** under the hood, you use whatever language you want.\n\n#### › Update\n\nTo update **Lagune**'s own files and its commands to their latest versions, run:\n\n```bash\nnpx -y lagune@latest update\n```\n\n> [!TIP]\n>\n> Your charter, the phase artifacts, and any custom specializations stay untouched.\n\n#### › Pull\n\nWhen you clone or fork a project that already has **Lagune**, run pull to install its files from the manifest:\n\n```bash\nnpx -y lagune@latest pull\n```\n\n> [!TIP]\n>\n> 💡 Think of it as the **Lagune** equivalent of `npm i`, `pip install -r requirements.txt`, and the like.\n\n---\n\n### Slash Commands\n\nOnce **Lagune** is set up in your project, your **AI** agent unlocks a set of slash commands:\n\n#### › Development flow\n\nSecure the work as you build it, guided by the charter, with no flow to follow:\n\n| Command                                               | What it does for you                                                      |\n| ----------------------------------------------------- | ------------------------------------------------------------------------- |\n| [**\u002Flagune**](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fcommands\u002Flagune) | Enforces security along with your development, on any prompt, at any time |\n\n- Pull in the on-demand specializations in real time while your agent works.\n- Combine it with the [**\u002Flagune.charter**](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fcommands\u002Fcharter) command to shape every build around your project's own security rules.\n\n#### › The Blue Team flow\n\nThese five run in order. Each builds on the previous, so following the list top to bottom is all it takes:\n\n| #   | Command                                                        | What it does for you                                                           |\n| --- | -------------------------------------------------------------- | ------------------------------------------------------------------------------ |\n| 1   | [**\u002Flagune.charter**](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fcommands\u002Fcharter) | Sets your project's security rules, proposed for you or shaped by what you say |\n| 2   | [**\u002Flagune.detect**](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fcommands\u002Fdetect)   | Reads your code and maps what your system does and where the risks are         |\n| 3   | [**\u002Flagune.plan**](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fcommands\u002Fplan)       | Turns what detect found into a defense plan, with a fix for each finding       |\n| 4   | [**\u002Flagune.harden**](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fcommands\u002Fharden)   | Applies the plan's fixes to your code, safely and one at a time                |\n| 5   | [**\u002Flagune.verify**](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fcommands\u002Fverify)   | Proves each applied fix holds and closes out the ones that do                  |\n\n#### › Special commands\n\n| Command                                                              | What it does                                                                            |\n| -------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |\n| [**\u002Flagune.specialize**](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fcommands\u002Fspecialize) | Specializes **Lagune** in a new security _sub_-skill from articles, exploits, or topics |\n| [**\u002Flagune.prove**](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fcommands\u002Fprove)           | Turns each detected finding into a runnable proof for responsible disclosure            |\n\n> [!TIP]\n>\n> Security is not a cost, it is an investment: what you put in upfront, you save many times over in the incidents you never have 🙋🏻‍♂️\n\n> [!IMPORTANT]\n>\n> See the full [**documentation**](https:\u002F\u002Flagune.ai\u002F) for usage examples and more.\n\n---\n\n## Requirements\n\nYou will need these tools installed on your system:\n\n- [**Node.js (LTS)**](https:\u002F\u002Fnodejs.org\u002Fen\u002Fdownload\u002Fpackage-manager)\n- At least one of the [**Supported Agents**](https:\u002F\u002Flagune.ai\u002Fdocs\u002Fsupported-agents)\n\n---\n\n## Security\n\nTo details, report a vulnerability, and see the supported versions, see the [**Security Policy**](https:\u002F\u002Fgithub.com\u002Fwellwelwel\u002Flagune\u002Fblob\u002Fmain\u002FSECURITY.md).\n\n---\n\n## Contributing\n\n🚧 Coming Soon.\n\n---\n\n## Acknowledgements\n\n### Partners\n\nPartners get an exclusive logo across the repositories and landing pages, plus a spot on a dedicated partners page.\n\n> Help my work grow by [**becoming a partner**](https:\u002F\u002Flagune.ai\u002Fdocs?partners) 🖖\n\n### Supporters\n\nReally thanks to everyone who has supported and keeps supporting my work.\n\n[![Sponsors](https:\u002F\u002Fwellwelwel.github.io\u002Fwellwelwel\u002Fsponsors.svg?v=1)](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fwellwelwel)\n\n> Support my work by [**becoming a sponsor**](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fwellwelwel) too ✨\n\n---\n\n## License\n\n**Lagune** is under the [**MIT License**](https:\u002F\u002Fgithub.com\u002Fwellwelwel\u002Flagune\u002Fblob\u002Fmain\u002FLICENSE).\u003Cbr \u002F>\nCopyright © 2026-present [**Weslley Araújo**](https:\u002F\u002Fgithub.com\u002Fwellwelwel) and [**contributors**](https:\u002F\u002Fgithub.com\u002Fwellwelwel\u002Flagune\u002Fgraphs\u002Fcontributors).\n\n> [!IMPORTANT]\n>\n> ### Disclaimer\n>\n> All product names, trademarks, and registered trademarks mentioned are the property of their respective owners and are used for identification purposes only.\n","Lagune 是一个面向软件开发全周期的安全增强工具，通过 AI 代理自动分析代码行为并指导针对性安全加固。它支持 37 种主流 AI 代理（如 Claude、Codex），无需 API 密钥，可在本地运行；提供 CLI 和交互式仪表盘两种使用方式，兼容任意编程语言项目。核心能力包括代码语义理解、安全风险识别、规范驱动的加固建议（如基于 SDD\u002FSDH）及 prompt 工程优化。适用于开发团队在构建阶段嵌入安全实践，或蓝队人员开展代码审计与合规性评估。","2026-07-11 02:30:38","CREATED_QUERY"]