By kawazy666
Repository knowledge curator named after Lordgenome — the biological supercomputer in Tengen Toppa Gurren Lagann. Captures the 'why' behind code — design decisions, history, trade-offs — that source alone cannot tell. Stores everything as Markdown under .lorgen/ so humans and AI agents both read and grow the same knowledge base. Also runs Knowledge-grounded multi-agent code review via /lorgen:review.
Knowledge-grounded code review. Checks a code change (staged/working diff, commit range, GitHub PR, or path filter) against the repo's curated `.lorgen/knowledge/`, `.lorgen/wiki/`, `.lorgen/adr/`. Orchestrates a 4-role multi-agent team — Coordinator (this skill, running in the main agent) plus three Task-spawned subagents: Knowledge Searcher → parallel Knowledge Investigators → Code Comparator. Surfaces conflicts with past decisions, conventions, lessons. Optionally writes new lessons / source updates back via Lorgen's redact pipeline. Activate when the user invokes `/lorgen:review`, asks for "Knowledge と照合した review", or types phrases like "過去の決定と整合してる?", "lesson に違反してない?".
Operating manual for Lorgen, the repository-knowledge curator. Activate when the agent invoked is the `lorgen` subagent, or when the user asks the main agent to "ask lorgen", "record this in lorgen", "onboard lorgen", or anything involving the `.lorgen/` directory, "why" questions about codebase history/decisions, or persisting design context across sessions.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
ソースコードだけでは語れない**「なぜそうなっているか」**(設計判断、 経緯、トレードオフ、教訓) を捕捉・蓄積する。すべてをリポジトリ内の Markdown として保存するので、人間と AI エージェントの双方が同じ知識 ベースを読み、育てていける。
生体コンピュータ Lorgen。記憶と知識の集積体 としてヒトの叡智を蓄え、必要なときに引き出す ── そんな役割を本 プラグインがリポジトリに対して果たす、というイメージ。
Lorgen は Claude Code プラグインとして配布される。一度インストール すれば、「なぜ」を捕捉・取得したい全リポジトリで使える。
lorgen) ── プラグインソース + 自身のデータlorgen/
├── .claude-plugin/
│ └── plugin.json # プラグインマニフェスト (name, version, ...)
├── agents/
│ └── lorgen.md # subagent 定義
├── skills/
│ ├── lorgen/ # 操作マニュアル (multi-file skill)
│ │ ├── SKILL.md
│ │ ├── schema.md
│ │ ├── retrieval.md
│ │ ├── accumulation.md
│ │ ├── sources.md
│ │ ├── onboard.md
│ │ ├── logging.md
│ │ └── metrics.md # logs → metrics の compile contract
│ └── review/
│ └── SKILL.md # 4-role multi-agent code review (main-agent skill)
├── commands/
│ └── review.md # slash command エントリ (/lorgen:review)
├── hooks/
│ └── hooks.json # PreToolUse: Write|Edit redaction guard
├── bin/
│ ├── lorgen-pretool-guard # hooks/hooks.json から呼ばれる
│ ├── lorgen-redact-check # secret パターンスキャナ (exit 1 = ブロック)
│ ├── lorgen-redact # redact ラッパー (stdout)
│ └── lorgen-compile-metrics # jq のみで動く決定論的 compile
├── .lorgen/ # データストア (このリポ自身。dogfood)
│ ├── config.yaml (tracked)
│ ├── .gitignore (tracked) cache/ + state.json + logs/ を除外
│ ├── knowledge/ (tracked)
│ │ ├── conventions/
│ │ └── decisions/
│ ├── wiki/ (tracked)
│ │ ├── overview.md
│ │ └── architecture.md
│ ├── adr/ (tracked) outputs.write_adr=true 時にのみ生成
│ │ └── 0001-<slug>.md
│ ├── metrics/ (tracked) per-session 集計 JSON
│ │ └── 20260429-102345-a3f9c2.json
│ ├── logs/ (gitignored) raw per-session JSONL
│ ├── cache/ (gitignored)
│ └── state.json (gitignored)
├── docs/
│ └── architecture.md # 長文アーキ概要 (living doc)
└── README.md
/plugin install lorgen 後)your-app-repo/
├── .claude/
│ └── plugins/
│ └── lorgen/ # インストール済みプラグイン (project scope)
│ ├── .claude-plugin/plugin.json
│ ├── agents/lorgen.md
│ ├── skills/lorgen/...
│ ├── hooks/hooks.json
│ └── bin/lorgen-* # redact-check, compile-metrics ほか
├── .lorgen/ # Lorgen のデータストア (初回利用時に生成)
│ ├── config.yaml (tracked) チーム共有設定
│ ├── .gitignore (tracked) cache/ + state.json + logs/ を除外
│ ├── knowledge/ (tracked) Knowledge アイテム
│ │ ├── conventions/
│ │ ├── decisions/
│ │ ├── runbooks/
│ │ ├── facts/
│ │ └── lessons/
│ ├── wiki/ (tracked) Wiki ページ
│ ├── adr/ (tracked) outputs.write_adr=true 時に生成
│ │ ├── 0001-decimal-money.md # Lorgen が生成した ADR
│ │ └── 0002-aurora-migration.md
│ ├── metrics/ (tracked) per-session compile 済み集計
│ │ ├── 20260429-102345-a3f9c2.json # path / count / timestamp のみ
│ │ ├── 20260429-110512-c8f2d4.json # 集約による privacy 担保
│ │ └── 20260430-091205-b1e3a7.json
│ ├── logs/ (gitignored) raw per-session JSONL
│ │ └── 20260429-102345-a3f9c2.jsonl # セッション末で metrics/ に compile
│ ├── cache/ (gitignored) PR/issue/LLM の生キャッシュ
│ └── state.json (gitignored) onboard カーソル, indexing state
└── (アプリケーションコード)
3 つの構成要素:
agents/, skills/lorgen/, hooks/, bin/,
.claude-plugin/plugin.json) はこのリポジトリにのみ存在する。
/plugin install 時に .claude/plugins/lorgen/ (プロジェクト) または
~/.claude/plugins/lorgen/ (ユーザー) へコピーされる。.lorgen/) は各ユーザーリポジトリで初回利用時に
作成される。Knowledge / Wiki / Metrics は tracked、raw logs は
gitignored。.lorgen/adr/) は outputs.write_adr が true、または
per-record で opt-in したときにのみ書き出される。デフォルトはオフ。
リポジトリ慣習に合わせて出力先を outputs.adr_dir で docs/adr/
などへ上書き可能。npx claudepluginhub kawazy666/lorgen --plugin lorgenUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation