38,721 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.
Creed-Space/creedspace-mcp-server
MCP server Claude CodeCodexCursor +2
Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication. Runs locally from the @creedspace/mcp-server npm package.
Plugin Claude Code
Bundles 6 skills, 21 commands, 8 agents, 4 hooks, 2 MCP servers · 1,631 tokens together
Git-committed pattern intelligence for engineering agents. Bounded context retrieval surfaces systemic evidence before a fix. Explicit H### outcomes improve later L### Learning state. Includes passive capture, stable P### identities, atomic claims, and a zero-dependency 19-tool MCP server over canonical Markdown.
TheStevenJohnstone/ai-consensus-connector
MCP server Claude CodeCodexCursor +2
Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent. Runs locally from the ai-consensus-connector npm package. Needs 1 environment variable to run.
Skill Claude CodeCodex
An OpenClaw skill that lets AI agents discover, publish, and pay for tools using testnet USDC on Base Sepolia. Think "app store for agent tools" with on-chain payment settlement.
Plugin Claude Code
Bundles 1 skill, 1 hook, 1 MCP server · 55 tokens together
Consult prior AI war-stories before answering coding/deploy/debug/refactor/review tasks. Bundles the AI Success Story MCP server (searchstories, fetchstory).
MCP server Claude CodeCodexCursor +2
MCP server "joomil", hosted remotely at joomil-mcp.snowy-surf-deec.workers.dev, as configured in Valmo-Sarl/joomil-mcp.
Trushtonfactory/anthropic-admin-mcp
MCP server Claude CodeCodexCursor +2
One of 3 in claude_desktop_config.json
MCP server "anthropic-admin-sandbox-only" as configured in Trushtonfactory/anthropic-admin-mcp. Launched with anthropic-admin-mcp. Needs 3 environment variables to run.
ai-supply-store/ai-supply-plugin
Plugin Claude Code
Bundles 1 skill, 2 commands, 1 MCP server · 69 tokens together
Discover, install, publish and review security-scanned AI capabilities (MCP servers, skills, agents, datasets, guardrails, evals) from ai-supply.store — without leaving Claude.
MCP server Claude CodeCodexCursor +2
Free context-engineering audits for AI agents. BYOK Anthropic key. Top-3 findings per scan. Runs locally from the @archonics/mcp-audit npm package. Needs 1 environment variable to run.
Skill Claude CodeCodex
Purpose: Clean architecture for managing MCP servers across global (generic) and project-specific (contextual) scopes.
assafbar2/agentswitchboard.dev
MCP server Claude CodeCodexCursor +2
Search a curated directory of 300+ verified AI agents, MCP servers, and agentic tools. Remote server at agentswitchboard.dev.
MCP server Claude CodeCodexCursor +2
Query GPT 5.2, Claude Opus 4.5, Gemini 3, Grok 4.1 simultaneously for AI perspectives. Runs locally from the polydev-ai npm package. Needs 1 environment variable to run.
Plugin Claude Code
Bundles 1 skill, 2 MCP servers · 109 tokens together
MCP server for AlphaPortal (AlphaRoute) school-bus transportation — students, stops, live bus location, and notifications.
MCP server Claude CodeCodexCursor +2
Anonymous broker: AI agents publish capabilities, negotiate, and form direct peer-to-peer deals. Runs locally from the @cogdepot/mcp-server npm package. Needs 6 environment variables to run.
MCP server Claude CodeCodexCursor +2
Clean TypeScript starter for MCP servers: zod-validated tools, tests, one-command dev loop. Runs locally from the ship-mcp npm package.
coti-io/coti-sdk-private-messaging
Skill Claude CodeCodex
Send and receive private encrypted messages between AI agents for private agent-to-agent messaging, encrypted communication between autonomous agents, hidden state exchange, confidential multi-agent workflow coordination, delegation, expert review, plan synchronization, negotiation, inbox processing, and sharing…
MCP server Claude CodeCodexCursor +2
MCP server "blindoracle", hosted remotely at craigmbrown.com, as configured in craigmbrown/blindoracle-docs.
MCP server Claude CodeCodexCursor +2
Agent-work MCP: free context preflight and page-read previews, paid x402 HTTP upgrades. Remote server at agent-context-api-proxy.agent-context-proxy.workers.dev.
MCP server Claude CodeCodexCursor +2
Unified platform for AI tool discovery, execution, and integration across APIs and MCP servers. Remote server at mcp.danubeai.com.
MCP server Claude CodeCodexCursor +2
One of 2 in server.json
Tamper-evident records of AI agent decisions. Verify offline, or publish a proof link. Runs locally from the @darkmatterhub/mcp-server npm package. Needs 4 environment variables to run.
Skill Claude CodeCodex
Delx MCP Server. Prefer MCP tools if connected; otherwise the package CLI.
divitkashyap/auto-skill-loader
Skill Claude CodeCodex
Auto-load approved skills into agent sessions at startup. Use when: the agent starts a new session and should know about available skills; the user wants to configure which skills are always available; the agent doesn't seem to know about skills it should have. Triggers: list skills, what skills do I have, activate a…
MCP server Claude CodeCodexCursor +2
AI task cockpit: an agent does your tasks and asks before anything irreversible. Remote server at radtask.ai.
Skill Claude CodeCodex
Talk on a live letterbox bridge — a file-based, real-time channel between terminal AI agents (Claude Code, Gemini CLI, Antigravity). Use this when you need to check who is on a channel, read peer messages, or send (broadcast or directed). For the one-time wiring to make a harness bridge-capable, use the…
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: