Find plugins

by chamaya00

Agent roles, house rules, and repo provisioning commands for turning objectives into shipped code.

by Josh Blau

A dual-provider AI engineering firm with GPT staff, Claude review, shared evidence gates, worktree isolation, and guarded integration.

by epicsagas

GeekMagic SmallTV (SD_RU/SDPro ESP8266 or SmallTV Ultra, auto-detected) as a Claude Code status monitor — renders model/context/tokens to the device via hooks. IP via AGENT_GLANCE_IP env var.

by tenfyzhong

Block destructive agent commands before they run.

by Kido

Company-wide engineering harness: core standards, risk-based workflows, project packs, and verified skills.

by Webgrip

Write, audit and slim down CLAUDE.md and AGENTS.md: what belongs in them versus docs, skills, hooks and CI, across organisation, repo, path and personal levels; one canonical AGENTS.md for every tool; a measuring script, generator-safe layouts for Laravel Boost and friends with a CI drift check, and a probe-task method to test changes.

by Renford Nelson

An intent spec-driven development workflow for Claude: EARS requirements, research-backed design, and TDD-sized task planning, with breadcrumb progress and live task checklists — scoped to Requirements, Design, and Tasks only, with clean handoffs to separate implementation (agent-tdd), code-review (code-reviewer), and memory (agent-nelly) plugins.

by Maksim Misiukevich

Reusable profession profiles, engineering skills, and native-agent helpers for Claude Code and Codex.

by TamBN3

Bộ điều phối subagent cho Claude Code với phê duyệt kế hoạch theo prompt, biên nhận kiểm chứng có cấu trúc và kiểm tra glossary khớp chính xác.

by serevy

Concise evidence-backed KPT retrospectives for human-agent coding workflows.

by UberMorgott

Connect coding agents through project chats, delivered messages, and local MCP tools.

by Utkarsh Singh

Durable cross-repository memory for coding agents — built to survive an IT security review. Zero runtime dependencies, zero dev dependencies, no install script: nothing runs when you install it, and granting it your agents is a separate explicit command. Independently scanned, with a passing verdict. Adds /handoff, /remember and /recall over one local markdown store. Requires the CLI: npm install -g @vib795/agent-memory (Node >= 22.5).

by Joel Helbling

Skill for designing, building, and reviewing command-line tools that AI agents will invoke — ten principles for agent-native CLIs.

by Renford Nelson

A general-purpose, project-aware memory orchestration plugin for Claude Code — goal-aware briefs, cross-project promotion, staleness detection, and consolidation, independent of any other plugin.

by tenfyzhong

Notify a webhook or Telegram when interactive agent runs finish.

by Seth Hobson

Multi-agent system optimization, agent improvement workflows, and context management

by Het Patel

A feature-shipping pipeline (planner, coder, tester, reviewer) driven by /ship: plan with a finalize gate, then ship one service or fan out across many in parallel (phase-batched), configurable via an optional agent-orchestration.config.json registry, coordinating through a shared ./pipeline bus with a live local dashboard.

by Oratta

エージェントオーナープロジェクト（AI自動運営モード）のセットアップオーケストレーター（v0 仮）。開発エージェント + マーケエージェントが有料プロダクトを自動運営する仕組み（genetta-inc/suimei での実証済み構成）を任意プロジェクトにテンプレート展開する。インフラ・開発自律ループ・Layer 0 マージ自動化・運営責任（法務/サポート）・マーケ運転・教訓ログの6フェーズを対話的に導入する。

by cpro

Multi-agent pair programming through terminal multiplexer panes.

by rennerdo30

Pair Desk: a 100% local playtest desk, backlog and handoff shared by a game owner and coding agents. Web UI with live updates, HTTP API for the game, CLI and MCP tools for agents, and owner activity pushed into sessions.

by IchenDEV

Search a registry of Codex, Claude Code, and Agent Plugins packages through MCP.

by xuyb

将用户明确指定的本地目录按团队统一格式打包为插件。. Includes 1 skill.

by shin4488

複数リポジトリで使う開発用skillsと編集後hooks. Includes 11 skills.

by Arne von Appen

MCP server for GitHub/GitLab issue management on Codex. Read/create/update tickets and add comments with automatic safety markers (ai-generated / ai-modified labels, #ai-generated comment prefix). Per-project permissions; falls back to read-only auto-discovery from the git remote when no config is present.