Building agents plugins

3,747 tagged Building agents, measured the same way as everything else here.

Browse within: claude-code-plugin 274cli 120agents 100ai-coding 87LLM 86agentic-ai 77ai-tools 71skills 70agent-orchestration 53agentic-workflow 46agent 44claude-code-plugins 43Multi-Agent 42gemini 39

multi-agent-example

1273

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.

not rated 8 1mo ago A tokens not measured original MIT

talos

1275

evolplus/talos

Plugin Claude Code

Bundles 62 skills, 2 commands, 4 hooks · 4,502 tokens together

End-to-end SDLC orchestration kit for Claude Code, including role agents, slash commands, skills, rules, and runtime hooks.

not rated 8 1mo ago A tokens not measured original Apache-2.0

multi-llm

1276

beastlabai/multi-llm-plugin

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.

not rated 8 1mo ago A tokens not measured original MIT

gtm-brain-builder

1277

Andytoizer/gtm-brain-builder

Plugin Claude Code

Bundles 11 skills, 9 agents · 778 tokens together

Build a source-backed GTM Brain for your company with specialist agents, skills, Grill-me questions, MVP checklists, and session handoffs. Originally built for Freckle.io's company GTM brain, then repurposed into a public plugin anyone can use.

not rated 8 4mo ago A tokens not measured original MIT

claude-radar

1280

lemomo-ai/claude-radar

Plugin Claude Code

Bundles 1 skill · 122 tokens together

Review your Claude Code collaboration across 9 dimensions in 3 categories (Communication / Engineering / Outcome) — deterministic script-computed baselines, a free-form AI diagnosis, and 5-7 playbook-driven suggestions with pastable prompts and installable assets (hooks, CLAUDE.md sections, .mcp.json). Tracks score…

not rated 8 1mo ago A tokens not measured

allbeads

1282

thrashr888/AllBeads

Plugin Claude Code

Bundles 1 skill, 19 commands, 1 hook · 186 tokens together

Multi-repo orchestration for AI agent workflows. Aggregate beads across repositories, manage contexts, and coordinate distributed work.

not rated 8 13d ago A tokens not measured original MIT

harn

1283

rjx18/harn

Plugin Claude Code

Bundles 2 skills · 138 tokens together

Use Harn's assumption-impact workflow in Claude Code: find assumptions, write plans, lock plans, check diffs, and apply Harn state.

not rated 8 3mo ago A tokens not measured original MIT

aida

1284

LWTlong/aida

Plugin Claude Code

Bundles 13 skills, 1 command, 1 MCP server · 685 tokens together

AIDA — Local AI Asset Manager. MCP-first governance for rules, skills, docs, and plugins accumulated through long-term vibe coding.

not rated 8 1mo ago A tokens not measured original MIT

sanctuary-framework

1286

eriknewton/sanctuary-framework

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 120 tokens together

The open source standard for secure, private AI: operating-system enforcement is live on macOS today; Linux and Windows are not live enforcement yet, and your data stays under your own keys with current portability bounds called out in the Assurance Matrix. Wraps any MCP-compatible agent with encrypted state, approval.

not rated 8 today A tokens not measured original Apache-2.0

froglet

1287

armanas/froglet

Plugin Claude Code

Bundles 1 skill, 1 command · 47 tokens together

Connect Claude Code to a local Froglet node for verifiable compute, signed receipts, settlement, and service publication.

not rated 8 2mo ago A tokens not measured original Apache-2.0

webmcpify

1289

TueJon/webmcpify

Plugin Claude Code

Bundles 1 skill · 66 tokens together

WebMCP agent skill for curated core coverage or route-by-route parity — inventory an existing web app, integrate approved tools, then verify and heal them in a real browser.

not rated 8 +1 3d ago A tokens not measured original MIT

a2acast

1291

husker/a2acast

Plugin Claude Code

Bundles 1 skill, 3 hooks · 77 tokens together

Let this Claude Code session message and exchange A2A tasks with AI agents on other machines over an encrypted, zero-infrastructure mesh.

not rated 8 15d ago A tokens not measured original MIT

claudemon

1292

OriginalName457/claudemon

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 67 tokens together

A friendlier way to run Claude Code agents — your crew is a bunch of pixel creatures you can watch work. Plus Clawland, an .io brawler.

not rated 8 6d ago A tokens not measured original MIT

kibi-cursor

1293

Looted/kibi

Plugin Cursor

Bundles 1 command · 12 tokens together

Optional Cursor adapter for Kibi. Requires SWI-Prolog 9+ and project-local kibi-cli, kibi-mcp, and kibi-core before the bundled MCP server can start.

not rated 8 yesterday A tokens not measured AGPL-3.0

agent402

1294

MikeyPetrillo/Agent402

Plugin Cursor

Bundles 2 skills, 1 MCP server · 286 tokens together

Open-source MCP server with 500+ deterministic tools + 100 skill packs — web search, headless Chromium, PDFs, OCR, images, live data, x402 payments helpers, and 210 pure-CPU utilities. Free to self-host or pay per call in USDC on Base + 4 more chains (+ USDG on Robinhood Chain).

not rated 8 today A tokens not measured AGPL-3.0

awesome-agent-skills

1295

khasky/awesome-agent-skills

Plugin Claude Code

Bundles 42 skills · 5,515 tokens together

Skills for AI coding agents: code review, test writing, design docs, debugging, security and dependency audits, git history surgery, refactoring, copywriting, and cleaning up AI-written code and text. Every skill is a plain SKILL.md folder under the open Agent Skills standard, stack-agnostic, and ends with the check…

not rated 8 changed today A tokens not measured original MIT

hermes-blind

1296

hermes-labs-ai/hermes-blind

Plugin Claude Code

Bundles 1 skill · 61 tokens together

Local recovery anchors for Claude Code and Codex sessions, plus evidence-gated evaluation prompts.

not rated 8 +3 changed today 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: