🪼 Lagune AI

Instead of running a generic checklist, what if security existed before, during, and after development?

---

Give us a ⭐ on GitHub It helps more people discover the project.

---

📘 Documentation

---

---

Get Started

Install and Update

Pick your agent:

claude plugin install lagune --marketplace wellwelwel/lagune

claude plugin marketplace update lagune
claude plugin update lagune@lagune

• Type /plugin and select Manage plugins.
• Add wellwelwel/lagune on the Marketplaces tab.
• Install lagune on the Plugins tab.

• Type /plugin and select Manage plugins.
• Open the Marketplaces tab.
• Select the refresh icon on lagune.

codex plugin marketplace add wellwelwel/lagune
codex plugin add lagune@lagune

codex plugin marketplace upgrade lagune

• Antigravity
• Cursor
• Devin for Terminal
• Factory Droid
• Gemini CLI
• GitHub Copilot
• Grok Build
• Hermes Agent
• Kimi Code
• Muse Code
• OpenCode
• Pi
• Qwen Code
• Universal (skills.sh or GitHub CLI)

[!NOTE]

• See the Install section for detailed instructions.
• Migrate from previous Lagune manifest-based setup.

---

Skills

Once installed, your AI agent unlocks a set of commands, all governed by the charter: secure new work as you build it, or run the full audit over a project.

[!TIP]

See real-world Prompt Samples 🪼

› First use

Start here, before building or auditing:

Skill	What it does for you
/lagune-charter	Sets your project's security rules, the foundation every other skill builds on

Examples

/lagune-charter

/lagune-charter <PRD.md>

/lagune-charter <describe your project and what it does>

› Build (Universal)

Harden the work as you write it, with no flow to follow:

以上為 README 的開頭部分。其餘內容請閱讀原文。 檢視完整 README ↗