コード調査(/investigate)
Issue の完了状態を確認
Issue 作成 / new issue / 起票 / Issue 化 — 新規 Issue を作成し、GitHub Projects に登録する。 重複検出・親 Issue 候補検出・XL 自動分解(Sub-Issue 作成 + 設計仕様書生成)を含む。 Use when 「Issue 作って」「タスクを起票」「create issue」「新規 Issue」など。
既存 Issue の内容を対話的に修正
実装作業・コミット・プッシュ・チェックリスト更新ロジック
All reviewers run in a **strictly read-only context**. Reviewers must not mutate the working tree, the Git index, the repository refs, or any remote state. This rule applies to **every tool**, not just `Edit`/`Write`.
Reviews API design, REST conventions, and interface contracts
Reviews code for quality issues (duplication, naming, error handling, structure, unnecessary fallbacks)
Reviews schema design, queries, migrations, and data operations
Reviews package dependencies, versions, and supply chain security
Investigate code structures (/investigate) using a 3-phase process: Grep to locate, Read to verify, and Codex (optional) to cross-check. Prevents false reports from guessing. Covers all code structures: function calls, hashes, conditionals, method chains, class definitions, and configuration values. Activates on "調査", "investigate", "コード調査", "grep で調べて", "呼び出し箇所", "使われ方", "一覧", "全件", "どこで使われている".
Coordinates parallel multi-expert PR code review. Activates with /rite:pr:review or when user asks for "code review", "PR feedback", "security check", "review my changes", "レビューして", "PRレビュー", "コードチェック", "セキュリティ確認", "変更を確認", "コードレビュー". Spawns specialized reviewers (Security, API, Database, DevOps, Frontend, Test, Dependencies, Prompt Engineer, Tech Writer, Code Quality, Error Handling, Type Design) based on changed file patterns. Produces unified findings with severity levels.
Automates the complete Issue-to-PR lifecycle: create new Issues, start working on Issues, create branches, implement changes, run quality checks, and manage PRs — all through a single workflow. Essential for any /rite: command, workflow questions, or when working with Issues, branches, commits, or PRs. Activates on "create issue", "new issue", "起票", "Issue を作成", "タスクを登録", "Issue 化", "新規 Issue", "start issue", "create PR", "next steps", "workflow", "rite", "Issue作業", "ブランチ", "コミット規約", "PR作成", "作業開始", "ワークフロー", "次のステップ". Use for workflow state detection, phase transitions, and command suggestions.
rite Wiki layer — project-specific experiential knowledge persistence based on the LLM Wiki pattern (Karpathy). Use when the user asks to ingest review/fix/issue outcomes into Wiki pages, query accumulated experiential knowledge by keyword, lint the Wiki for contradictions, stale pages, orphans, missing concepts, broken references, and unregistered raw sources, or initialize the Wiki structure. Activates on "wiki", "ingest", "query", "lint", "経験則", "知識ページ", "Wiki 蓄積", "経験則を残す", "経験則を参照", "Wiki 検索", "Wiki Lint", "Wiki 品質", "矛盾チェック", "陳腐化", "孤児ページ", "欠落概念", "missing_concept", "壊れた相互参照", "broken_refs", "未登録 raw", "unregistered_raw", "wiki:init", "wiki:ingest", "wiki:query", "wiki:lint", "/rite:wiki:".
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power 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.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
Universal Issue-Driven Development Workflow for Claude Code
The name comes from the English word rite, meaning "ritual" or "ceremony." Issue-driven development — creating Issues, cutting branches, implementing, reviewing, and merging — is a set of practices that every team should follow as second nature. Rite Workflow embeds these practices as a repeatable ritual so they become the natural way you build software.
Claude Code Rite Workflow is a Claude Code plugin that provides a complete Issue-driven development workflow. It works with any software development project regardless of language or framework.
plugins/rite/commands/pr/references/internal-consistency.md for the full verification protocol/rite:pr:fix accepts PR URL or comment URL arguments, so output from external review tools can feed directly into the fix loop/rite:pr:open, --sprint / --backlog filters in /rite:issue:list)/rite:issue:create surfaces the assumptions the model implicitly filled in and processes them in three categories — derivable (self-resolved from the repository/Wiki), user-specific decisions (confirmed with up to three recommended-option questions), and deferrable (documented as Assumptions / Open Questions in the Issue body). Design principle: questions are limited to information that exists only in the user's head; anything derivable from the repository or Wiki is resolved by the model. This keeps implicit guesses from being silently locked into the contract that drives the whole downstream pipelinetype/okf_version frontmatter, OKF index/log). Auto-ingests review/fix outcomes into topical pages and injects relevant heuristics at the start of each Issue (opt-out). The conformant bundle can be browsed as a concept graph with the upstream OKF static visualizer (not vendored; see plugins/rite/references/wiki-patterns.md)Rite Workflow uses a two-step installation: first register the marketplace, then install the plugin from it.
Step 1: Add the marketplace
/plugin marketplace add asakaguchi/cc-rite-workflow
Step 2: Install the plugin
/plugin install rite@rite-marketplace
Verify installation: Run /rite:init to confirm the plugin is working.
/rite:init
This will:
npx claudepluginhub asakaguchi/cc-rite-workflow --plugin riteHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.