Skill Claude CodeCodex
Authoritative architecture reference for Lagune, covering repository layout, the command/template split, the core/adapter boundary, what it scaffolds, and the tracking-map model. Use before adding an agent or when a decision depends on repo shape.
Skill Claude CodeCodex
Authoritative reference for the Lagune dashboard, a live view of a project's .lagune/ chain with a locked-down local action surface. Use before changing anything under src/dashboard/ or src/types/dashboard/.
Skill Claude CodeCodex
Authoritative engineering reference for Lagune, covering the toolchain, code conventions, type rules, the build and distribution path, and how the tracking hooks work. Use before writing or changing source under src/ or test/, or before the build.
Skill Claude CodeCodex
Design engineering principles for making interfaces feel polished. Use when building UI, reviewing frontend code, or working on any visual detail, from animations, hover states, shadows, borders, and typography to optical alignment and tabular numbers.
Skill Claude CodeCodex
How to simulate a Lagune command end to end so the user sees both the process and the results in chat. Use when the user asks to simulate, demo, preview, run, or see in action any lagune command. Read this before attempting any such simulation.
Skill Claude CodeCodex
Author a new built-in Lagune sub-skill inside the Lagune source, not a scaffolded .lagune/ target. Use when adding or refining a security knowledge module that ships with Lagune, against the native layout (spec/skills/.md plus the catalog).
Skill Claude CodeCodex
Authoritative reference for writing Lagune's prose. Use before writing, editing, or translating any artifact, charter, command text, doc, or user-facing message.
Cursor rule Cursor
CLAUDE.md.
Instructions file GitHub Copilot
Instructions for wellwelwel/lagune, a project described as: 🌊 Lagune is your security copilot as you build, your Blue Team when you audit, whether you're a developer or not (no API key needed).
Instructions file CodexOpenCode
Instructions for wellwelwel/lagune, a project described as: 🌊 Lagune is your security copilot as you build, your Blue Team when you audit, whether you're a developer or not (no API key needed).
Instructions file
Instructions for wellwelwel/lagune, covering sdh (security-driven hardening): lagune, 1. what this workspace is, the problem it exists to solve, what lagune actually ships and flexible by design.
Instructions file Gemini CLI
Instructions for wellwelwel/lagune, a project described as: 🌊 Lagune is your security copilot as you build, your Blue Team when you audit, whether you're a developer or not (no API key needed).
Command
Establish or update the project's security charter, the safe-by-default principles every later phase must respect. Reads the project's files to learn what it is and uses, weighs any description you give against them, and asks when something is unclear.
Command
Detect what the system actually does by reading the code, and map the security-relevant findings (login, uploads, payments, data exposure, and so on) with the evidence later phases need. Scans the whole project, named files, or a focused scope.
Command
Apply the defense plan's fixes to the code, safely and one at a time, then record what was applied and what is left. Reads the plan and the charter, then hardens every fix, the fixes, files, or directories you name, or a priority you choose.
Command
Do the work the prompt asks for, with security guarding the build as it happens. Loads the charter, matches the security knowledge the work touches, builds safe-by-default, then checks its own result against what it used.
Command
Turn what detect found into the defense plan, one fix per finding, each rated by CVSS v4.0 (category, CVSS, priority) and tied to a charter principle. Reads the detect map and the charter, then plans every finding, named paths, or a concern you describe.
Command
Prove detected findings with runnable, defense-only evidence. For each finding the detect map carries, it writes a safe-path JavaScript test and a self-contained advisory under .lagune/proofs/. The test asserts secure behavior, never an exploit.
Command
Repair Lagune's internal tracking so each item stays whole when files are renamed or moved. A maintenance pass, not a security phase. It reads every artifact and the current code, then rewrites the tracking map across all phases in one pass.
Command
Specialize Lagune in a security area from a source or topic you give it, distilling it into a new on-demand sub-skill the detect and verify phases load later. It writes a focused, language-agnostic, defense-only knowledge module, never an exploit.
Command
Prove each applied control holds by confronting the hardening record with the code, writing each verdict back into that record, then standing the findings proven closed out of the chain. Read-only on your code, it writes only Lagune's own chain.