3,758 tagged Building agents, measured the same way as everything else here.
Browse within: claude-code-plugin 276cli 122cursor 103agents 102ai-coding 87LLM 86agentic-ai 75ai-tools 70skills 70agent-orchestration 53agent 50agentic-workflow 45claude-code-plugins 43Multi-Agent 42
Plugin Claude Code
Bundles 1 skill, 4 hooks, 2 MCP servers · 47 tokens together
Conduct AI CLI — run agents, manage workspaces, and enforce AI usage policies with ConductGuard MCP. Includes conduct, conductguard-mcp, and conduct-mcp binaries.
Plugin Claude Code
Bundles 1 skill, 2 MCP servers · 74 tokens together
Connect Claude Code to Civic's MCP Gateway for agent identity, scoped permissions, audit trails, and revocable access control.
voicelogica/voice-logica-plugin
Plugin Claude Code
Bundles 17 skills, 1 MCP server · 957 tokens together
Manage Voice Logica AI voice agents, phones, calls, workflows, integrations, SMS, and support tickets from Claude Code.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 69 tokens together
Connect to LLM Reference (llmref.org) for versioned, model-ready documentation and semantic search, with a skill that teaches the tool flow.
Evanyuan-builder/temporal-core
Plugin Claude Code
Bundles 1 skill · 95 tokens together
Research-backed temporal awareness for Claude Code agents — make agents feel time pass via lightweight hooks + skill.
Plugin Claude Code
Bundles 8 skills, 5 agents · 775 tokens together
Analyze codebases with deep, verified research and generate evidence-grounded Claude tooling — CLAUDE.md, path-scoped rules, skills, agents, hooks, and a verify backlog.
Plugin Claude Code
Bundles 1 skill, 2 commands · 48 tokens together
Stop your AI agent from coding before thinking. Enforces a plan-first workflow: understand, explore, plan, then implement. Reduces backtracking and wasted tokens.
Plugin Claude Code
Cost-optimized LLM model recommendations for AI agents. Get real-time pricing across 100+ models and find the cheapest model for any task.
Plugin Claude Code
Unified MCP server for the Devin API — sessions, knowledge, playbooks, secrets, schedules, attachments, and DeepWiki docs tools.
Plugin Claude Code
Bundles 3 skills, 2 hooks · 38 tokens together
Organization agent guardrails — policy-driven skills and hooks for Claude Code.
Plugin Claude Code
Bundles 1 skill · 116 tokens together
Interrogates recently shipped work with seven socratic questions, forcing evidence-backed answers about confidence, blind spots, decay, and unstated assumptions.
stoyan-stoyanov/agentcouch-plugins
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 169 tokens together
Hosted MCP messaging rooms across owners, clients, and machines, with authenticated account attribution and a human-readable transcript.
Plugin Claude Code
Bundles 1 skill · 122 tokens together
Reviews how a Claude Code session was conducted rather than what it shipped — classifies its shape, scores the run, flags where the context window went, and turns recurring cost into wire-ins for the skills it used or a named lever on the environment that caused it.
Plugin Claude Code
Bundles 12 skills · 732 tokens together
OATDA (One API To Direct All) — Unified access to 10+ LLM providers (OpenAI, Anthropic, Google, Deepseek, Mistral, xAI, Alibaba, MiniMax, ZAI, Moonshot, Bytedance) for text generation, vision analysis, image generation, video generation, audio generation/transcription/translation, model comparison, and balance…
Plugin Claude Code
Bundles 8 skills · 813 tokens together
A workflow of skills for creating, updating, judging, reviewing, evaluating, and auditing AI skills and agent definitions.
Plugin Claude Code
FocusMCP — MCP orchestrator that reduces AI context from 200k to 2k tokens. Compose AI tools (bricks) on demand without polluting context.
Plugin Claude Code
Bundles 4 skills, 1 hook · 409 tokens together
Reusable AI agent skills for Claude Code: camel-matrix, cc-best-practices, skill-best-practices, project-references.
Plugin Claude Code
Bundles 19 skills, 2 commands · 1,187 tokens together
Plugin that includes Skills for building AI agents and MCP servers on the Cloudflare developer platform.
Plugin Claude Code
Bundles 1 skill, 1 command · 43 tokens together
Dispatch Cursor CLI subagents from Claude Code (or any MCP-compatible client).
Plugin Claude Code
Bundles 4 commands · 71 tokens together
DSPEC speculative draft-then-verify: cheap model drafts, an independent gate scores, the target model verifies only surviving drafts. Approximate, not lossless.
Plugin Claude Code
Bundles 3 commands, 10 agents · 416 tokens together
Automated task consumption loop — parallel TDD implementation, adversarial testing, and architectural review using handoff-mcp sessions. Language and framework agnostic.
tboome33/openrouter-fusion-mcp
Plugin Claude Code
Bundles 1 skill, 1 command, 1 hook, 1 MCP server · 149 tokens together
OpenRouter Fusion (multi-model deliberation) MCP server + an interactive selector skill/command (list presets with cost → recommend → pick → reasoning → temperature) + a PreToolUse hook that confirms before every paid run.
Plugin Claude Code
Bundles 6 skills, 1 MCP server · 403 tokens together
Zihin Agent Builder — gerencie agentes de IA da plataforma Zihin direto do Claude Code: MCP server com 96 tools (agentes, schemas, triggers, budget, aprovações, observabilidade) + 6 skills especialistas com os playbooks e gotchas da plataforma.
Plugin Claude Code
Bundles 3 skills · 276 tokens together
Project-specific skills for the MacWright MCP server — Safari automation, screen coordinate system, tool development patterns, and workflows discovered during iterative testing.
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: