13509 plugins available.
by Ghast AI
Generate speech, transcribe audio and manage voices and pronunciation dictionaries through Cartesia’s official MCP server.
by SriBYJU
Adaptive model, reasoning, context, verification, and parallel-work orchestration for Codex.
by Markus
case-assist — fallgetriebene Subsumtionsassistenz (HTTP). Server ruft nie ein LLM: Client extrahiert selbst (extraction_prompt → submit_case).
by Oratta
意思決定移譲のフレームワーク「観点の配役」の実装プラグイン。catalog/catalog.md: 3グループ14観点・列定義・横断軸・変更手続き・変更記録を持つ観点カタログの唯一の正本。catalog/injection.md: 14観点の注入タイミング（9分類）・配線先機構・注入文書（.claude/casting/policies/）の置き場所規約を持つ注入マップの正本。skills/casting: 配役表（project.md/local.md/セッション宣言の3層）の作り方・判例台帳の書き方・カタログ変更手続きの手順正本。commands/init.md（/casting:init）: 対象 git repo に `.claude/casting/` 一式を雛形から生成し、gitignore に local.md を冪等追記する。scripts/casting-check.sh: 配役表の5列ちょうどに割れない壊れた表行・閉じられていない HTML コメント・閉じられていない Markdown のコードフェンス・未知の観点語彙・「カタログ外」判例・同一観点の「論点じゃなかった」2件以上・catalog_version 不一致・相談判例（経路「相談の上自走した」）の事後報告5要素欠落の8項目を検出する lint。resolve サブコマンドは有効配役表を合成して出力する（検証を通らない配役表では出力せず exit 1 の fail-closed）。rules/perspective-casting.md（このプラグインとは別ファイル）が毎ターン効く返信前チェック5手順を持つ薄い常時ロード層。 agents/casting-specialist.md（model: sonnet、tools: Read/Grep/Glob/WebFetch — 全文未把握の外部規約を判断前に参照先で読む）・agents/casting-arbiter.md（model: fable）: 論点相談・仲裁プロトコル（#127）の汎用サブエージェント。スペシャリストは指定された policies/<slug>.md を読み人格ブロックを纏って意見を返し、仲裁はフェーズ宣言文と主張リスト（メインセッションの主張1件＋各人格の主張1件ずつ）のみを入力に裁定する。templates/policy.md: 注入文書（人格ブロック＋判断基準＋前提とする外部規約）の雛形。catalog/delegation.md: 委任の定義正本（委任＝許可ツール × 任された観点。ロールは組み合わせ名。`## 委任` 配下に許可ツール表と任された観点表を並べる宣言書式。宣言は要約で正本は permission 設定と配役表 3 層）。commands/policy-interview.md（/casting:policy-interview <観点>）: 観点の判断基準を主と 1 問ずつやり取りして policies/<slug>.md を生成・更新する。templates/delegation.md: /casting:init が生成する委任宣言の雛形。
by Catalyst by Zoho
Build, deploy, and operate Catalyst by Zoho applications with official service, SDK, CLI, architecture, pricing, and Zoho MCP skills across eight supported data centers.
by Catalyst Shift
How Catalyst Shift operates (HOW_WE_BUILD v2). Three skills: next (the pickup loop — top Linear card → build → in-session adversarial pass → /ship with auto-merge on → next card, 650k context budget, handoff for a fresh session), ways-of-working (three homes + the build method: /next, adversarial review as a required check, auto-merge on everything, recommend-ask-proceed with hard stops), and decision-governance (proposed-vs-decided labelling, ratification rules). The verify skill and verify-gate hook are retired (the CI adversarial review replaces them). Behavior only; canon content stays in the strategy doc and docs/HOW_WE_BUILD.md.
Define category profiles, process preserved product archives into schema-governed silver data, review mapping gaps, and prepare interpretable pricing-model inputs.
Collect and preserve broad raw product information and original evidence before designing an analytical feature schema.
by CatWrangler
Bring your CatWrangler projects into Codex. Every session connects itself and picks up the right project's context — its decisions, its history, its code — so you skip the setup and get to work.
caveman is an open-source Codex plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.
Ultra-compressed communication mode. Includes 2 skills.
by Julius Brussee
Ultra-compressed communication mode. Cut filler. Keep technical accuracy.
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
by Carlos Araujo
Stable concise technical output for Codex, reinjected after session lifecycle and compaction events.
Estilo de saída estável, técnico e conciso para Claude Code.
by CB Insights
Research private companies, markets, deals, competitors, predictive signals, market maps, and investment questions through CB Insights' official hosted MCP server.
by suwa-sh
Claude Code 運用支援
by AnExiledDev
The unofficial Claude Code changelog, in your terminal
by jem0ntr053
Personal cross-project workflow: model-tier pre-flight, handoffs, session debrief, token-aware routing
by Ezio2000
Agent Enhance host adapter for Claude Code: one MCP server per capability, per-provider modules, provider logins
by roylam-beep
Claude Code 開發治理層：cc-* skill 家族、感測 hook、文件閘、骨架安裝器。
by RichardAtCT
An idle game that runs beside Claude Code, fed only by the work Claude does for you
Claude Code plugin for the mirza-bots fleet: contains the whole engine -- it polls this session's bot on Telegram, stores the fleet's shared history, and exposes reply/read_history/search_history as MCP tools. No daemon.
by Guillaume Lebedel
Export Claude Code or Codex conversations to terminal-styled PNG, SVG, PDF or HTML, with syntax highlighting, dark and light themes, and range selection (last N exchanges, from or until a topic).