38,263 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
naimax/agent-harness-reference
Cursor rule Cursor
A set of rules for an orchestrator that coordinates coding agents without writing the product code itself. It assigns work through tasks and passes handoffs through shared work items.
MCP server Claude CodeCodexCursor +2
Stdio-to-HTTP gateway — connects MCP clients to remote HTTP MCP servers. Runs locally from the mcp-stdio Python package.
Skill Claude CodeCodex
Drive a SPARDA compiled Behavior Runtime to its full potential. Use this whenever you are connected to a backend running the SPARDA Runtime (compiled into a Unified Behavior Graph - UBG) — recognizable by the tools spardagetcontext, spardainfo, spardaconfirm, or composite tools. It teaches the graph-context-first…
Skill Claude CodeCodex
Synchronize code assistant memory and consolidate memory across Claude Code, Codex CLI, Gemini CLI, Antigravity, Cursor, and Windsurf. Use when users want shared provider memory, global memory sync, memento sync, memory cleanup, or multi-assistant context portability.
bl1nk-bot/bl1nk-agents-manager
Skill Claude Code
บันทึกการเรียนรู้ ข้อผิดพลาด และการแก้ไขเพื่อการปรับปรุงอย่างต่อเนื่อง ใช้เมื่อ: (1) คำสั่งหรือการทำงานล้มเหลว (2) ผู้ใช้แก้ไขข้อมูล (3) ผู้ใช้ร้องขอความสามารถที่ไม่มี (4) API หรือเครื่องมือภายนอกล้มเหลว (5) พบแนวทางที่ดีกว่าสำหรับงานที่ทำซ้ำ หรือต้องการทบทวนการเรียนรู้ก่อนเริ่มงานสำคัญ.
Plugin Claude Code
Bundles 1 command, 1 hook · 17 tokens together
Run Claude Code unattended: cap the spend, sandbox execution, and get a signed receipt, enforced from outside the agent's own process by the covguard binary.
Skill Claude CodeCodex
Legacy routing table for hosts without native skill discovery: maps a request to the right specialist skill and defines composed flows such as review followed by a security pass. Use when running the pack on a pre-Agent-Skills setup, such as plain rules files or a custom orchestrator, that cannot match skills by…
unfor19/dynamic-instruction-protocol
Cursor rule Cursor
Dynamic Instruction Protocol (DIP) – a flexible, Markdown-based approach to generate API commands on the fly with AI.
Command Claude Code
You are running the squadai squadai-init routine: read the current repository, understand what it actually contains, and refine each configured agent's role files (or solo instructions file) so they are tuned to this codebase — without losing any methodology semantics squadai installed.
Cursor rule Cursor
GraphStack v4.7.1 — Orchestrated, graph-first, GNAP-tracked AI development (cross-platform).
Cursor rule Cursor
Behavioral rules for LLM coding. Use when writing, reviewing, debugging, or refactoring code to read existing patterns first, avoid over-engineering, make surgical changes, manage dependencies, verify behavior, and communicate uncertainty.
Infopibe/everything-claude-code
Plugin Claude Code
Bundles 17 skills, 31 commands, 8 agents · 1,191 tokens together
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use.
geniro-io/geniro-claude-harness
Plugin Claude Code
Bundles 37 skills, 8 agents, 1 hook · 4,218 tokens together
Production-grade Claude Code harness with AI-driven setup, multi-agent skills, and safety hooks. Includes /setup for project-tailored configuration.
Cursor rule Cursor
Reference skills, agents, and commands by their registered name (never by filesystem path), and decompose oversized commands or agents by extracting sections into skills with by-name references.
Plugin Claude Code
Bundles 10 skills, 1 hook · 1,057 tokens together
Live multi-agent orchestration: WebSocket server + A2A messaging + dashboard + Stop hook helper + MCP server (full Phase 2 impl: WS proxy + 5 tools incl. a2awaitack 3-tier + session-lifecycle + §13.13.2 dedup + chunked transfer reassembly). v0.3.29 / Constellation v2.4.57 — room artifacts + board state schema: the re.
Skill Claude CodeCodex
A skill for creating and running teams of AI agents from a natural-language request. The description is written in Korean and refers to research teams and the /kkirikkiri command.
Plugin Claude Code
Bundles 1 skill, 3 commands · 174 tokens together
Analyze and optimize CLAUDE.md files using Anthropic's best practices for prompt engineering, XML tags, and memory patterns.
Skill Claude Code
Extract tacit engineering knowledge through guided interviews and generate structured steerings. Use when user mentions "steerings", "tacit knowledge", "conventions", "engineering practices", "interview", or wants to document team/project knowledge. Also activates when user asks for "steerings for X", "document X…
madciapka/gemini-claude-plugin
Plugin Claude Code
Bundles 3 skills, 9 commands, 3 agents · 361 tokens together
Use Gemini CLI from Claude Code to delegate tasks, run code reviews, and get adversarial design feedback.
Plugin Claude Code
Bundles 1 skill, 1 command · 48 tokens together
Conduct structured multi-perspective debates using 4 specialized subagents (FOR, AGAINST, NEUTRAL, and Scribe/Moderator) to stress-test ideas and reach well-reasoned conclusions.
jamesgray-ai/handsonai-plugins
Plugin Claude Code
Bundles 1 skill, 2 commands, 4 agents, 2 hooks · 580 tokens together
A complete, runnable worked example of multi-agent orchestration. Four specialist agents research, write, edit, and publish a business article, with automatic delegation, machine quality gates, and an enforced human approval step. Built to be read and adapted, not used as-is.
jeongsk/glm-coding-plan-statusline
Plugin Claude Code
Bundles 1 command · 7 tokens together
Configure a custom status line for Claude Code to display contextual information like model name, directory, and git branch at the bottom of the interface.
Plugin Claude Code
Bundles 62 skills, 2 commands, 5 hooks · 4,502 tokens together
End-to-end SDLC orchestration kit for Claude Code, including role agents, slash commands, skills, rules, and runtime hooks.
Plugin Claude Code
Bundles 1 skill · 146 tokens together
Orchestrate plan reviews, task generation, implementation, and code reviews in parallel across 13 coding harnesses (Codex, Cursor, opencode, pi, aider, Antigravity…) — or ask every model a free-text question about a plan.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: