Building agents plugins

3,736 tagged Building agents, measured the same way as everything else here.

Browse within: claude-code-plugin 282LLM 104agents 102cli 101ai-coding 94agentic-ai 80skills 73ai-tools 72agent-orchestration 52agent 49Multi-Agent 45agentic-workflow 44claude-code-plugins 42mcp-server 36

cobrew

553

buiducnhat/cobrew

Plugin Claude Code

Bundles 9 skills · 393 tokens together

Workflow skills and shared instructions for coding agents.

not rated 48 2mo ago A tokens not measured

mega-code

554

wisdomgraph/mega-code

Plugin Claude Code

Bundles 9 skills · 195 tokens together

Self-Evolving AI Coding Infrastructure — Generate, Curate, and Enhance Reusable Wisdom.

not rated 47 2mo ago A tokens not measured

gpt2agent

559

robotlearning123/gpt2agent

Plugin Claude Code

Bundles 2 skills · 274 tokens together

Your ChatGPT Plus/Pro account (chat, deep research, image gen, code, agent mode) as 25 MCP tools — reuses your codex login. Requires the gpt2agent CLI on PATH (pipx install gpt2agent).

not rated 47 1mo ago A tokens not measured original MIT

niksacdev/engineering-team-agents

Plugin Claude Code

Bundles 16 agents · 1,981 tokens together

8 specialized agents for collaborative software engineering: Product Manager, UX Designer, System Architect, Code Reviewer, Technical Writer, Responsible AI, GitOps Specialist, and Sync Coordinator.

not rated 47 1mo ago A tokens not measured original MIT

everruns-dev

561

everruns/everruns

Plugin Claude Code

Bundles 1 skill, 8 commands · 189 tokens together

Interact with the Everruns(Dev) managed harnesses platform. Manage harnesses, agents, and capabilities. Run agentic sessions. Create and deploy agentic applications.

not rated 47 today A tokens not measured original MIT

ccteams

562

toffyui/ccteams

Plugin Claude Code

Bundles 3 skills · 80 tokens together

Agent-team package manager for Claude Code. Provides slash commands to list, select, and apply pre-built agent teams to the current project.

not rated 47 changed 3d ago A tokens not measured original MIT

claudit

566

acostanzo/quickstop

Plugin Claude Code

Bundles 4 skills, 6 agents · 345 tokens together

Audit and optimize your Claude Code configuration. Caches current Claude Code ecosystem knowledge so any subsequent agent task — building a skill, configuring an MCP, authoring CLAUDE.md — can read it instead of re-fetching docs.

not rated 46 3mo ago A tokens not measured original MIT

skills

568

Randroids-Dojo/skills

Plugin Claude Code

Bundles 11 plugins

Portable Agent Skills with Codex metadata and Claude Code plugin packaging.

not rated 46 changed 3d ago A tokens not measured original MIT

swarmclawai/andrej-karpathy-skills

Plugin Claude Code

Bundles 1 skill · 46 tokens together

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

not rated 46 +4 3mo ago A tokens not measured original MIT

makoto

571

Clear-Sights/Makoto

Plugin Claude Code

Bundles 3 commands, 6 hooks · 36 tokens together

Holds Claude Code to its word — every claim checked against the agent's own logged record; faked checks blocked, not warned (four narrow advisory self-checks excepted). Two-tier catalog (15 pre-checks, 19 Stop gates), each shipped at measured zero false positives.

not rated 45 changed 3d ago A tokens not measured original Apache-2.0

skillify

572

0xMH/claude-skillify

Plugin Claude Code

Bundles 1 skill · 26 tokens together

Capture repeatable session workflows into reusable SKILL.md files. An open-source reimplementation of the internal /skillify skill.

not rated 45 5mo ago A tokens not measured original MIT

zero-review

574

A7um/zero-review

Plugin Claude Code

Bundles 5 skills, 9 commands, 1 hook · 304 tokens together

Auto-dev platform for agent-majority software teams. Five skills (auto-dev, auto-env, auto-req, auto-test, auto-triage), four roles (dev-agent, req-agent, user-agent, triage-agent), and cross-skill contracts. Humans supply requirements and intervene at key decision points; agents handle everything else.

not rated 45 2mo ago A tokens not measured original MIT

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: