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 88LLM 86agentic-ai 78ai-tools 71skills 70agent-orchestration 53agentic-workflow 46agent 44claude-code-plugins 43Multi-Agent 42gemini 39

zuvo

1394

greglas75/zuvo

Plugin Claude Code

Bundles 57 skills, 47 agents, 5 hooks · 6,749 tokens together

Multi-agent skill ecosystem for structured software development. 58 skills and 26 specialized agents with quality gates, code exploration, and evidence-based review.

not rated 6 changed 5d ago A tokens not measured original MIT

redeye

1395

Bitmia-ai/RedEye

Plugin Claude Code

Bundles 10 commands, 13 agents, 1 hook · 410 tokens together

Autonomous dev agent — works through your task list while you sleep. Zero config after install. Builds, reviews, deploys, and verifies each task end-to-end.

not rated 6 3mo ago A tokens not measured original MIT

gecko-surf

1398

GeckoVision/gecko-surf

Plugin Claude Code

Bundles 6 skills, 2 commands, 2 agents · 1,131 tokens together

Make any API agent-usable — even one with broken docs, no OpenAPI, a WAF, or an auth wall. Comprehend a spec (or JS-rendered docs) into first-call-correct MCP tools your agent calls right the first time, with auth injected and no integration code. On a painful real API, first-call-correctness goes from 10% to 65%…

not rated 6 2d ago A tokens not measured original Apache-2.0

coding-discipline

1399

chipfighter/coding-discipline

Plugin Claude Code

Bundles 8 skills, 2 hooks · 656 tokens together

Workflow-agnostic guardrails for AI coding agents: spec-sync preserves confirmed intent across sessions; brainstorming, TDD, root-cause debugging, prioritized review, evidence-before-done, disciplined git, and context hygiene trigger only when their risk conditions match. Includes a SessionStart discipline primer…

not rated 6 1mo ago A tokens not measured original MIT

helm

1401

sykoramade/helm-skill

Plugin Claude Code

Bundles 28 skills, 15 agents, 1 hook · 3,553 tokens together

HELM — run a project with a project-specific AI team: you are the MD, HELM is the CEO, and specialists are auto-invoked at deterministic lifecycle gates. Local-only, no telemetry.

not rated 6 1mo ago A tokens not measured original MIT

ai-crew

1402

Goktug/ai-crew

Plugin Claude Code

Bundles 24 skills, 8 commands, 7 agents, 1 hook · 1,676 tokens together

Production-grade Claude Code plugin that takes any React Native or TypeScript backend task from idea to PR with one human checkpoint. A Fable 5 team-lead orchestrates the full lifecycle inline, dispatching sonnet-, opus-, or fable-developers (routed per task by a complexity flag) and Haiku web-researchers under strict.

not rated 6 2mo ago A tokens not measured original MIT

build-verify-loop

1404

legacybridge-tech/claude-plugins

Plugin Claude Code

Bundles 1 skill · 94 tokens together

Self-iterating autonomous orchestration loop. The main agent spawns isolated Implementor and Critic subagents in rounds until the artifact converges, an iteration cap is hit, or human escalation is needed. Domain-agnostic — code, docs, plans, designs, copy, specs. Alias: bvl.

not rated 6 3mo ago A tokens not measured original MIT

codex-delegate

1406

yongop/codex-delegate

Plugin Claude Code

Bundles 1 skill, 1 agent · 171 tokens together

Plan with Claude, implement with OpenAI Codex — a cross-model delegation workflow with plan cross-review, scoped delegation units, and hard-won guard rails.

not rated 6 24d ago A tokens not measured original MIT

shiiman-claude

1409

shiiman/claude-code-plugins

Plugin Claude Code

Bundles 4 skills · 402 tokens together

A project-configuration tool for Claude Code, including its connections to external services and its command-line program.

not rated 6 2mo ago A tokens not measured

ai-agents-skills

1411

Xakki/ai-agents-skills

Plugin Claude Code

Bundles 23 skills, 3 agents, 6 hooks · 2,103 tokens together

Skills + hooks for Claude Code: teamlead (main thread as team-lead: delegate code work to subagents, surface only decisions), roadmap (plan & autonomously build a whole app phase-by-phase), kanban (manage a .claude/kanban board), schedule-tasks (auto-pilot todo cards via at/tmux), git-flow (shared git core: commits.

not rated 6 22d ago A tokens not measured original MIT

leapfrog-skill

1412

safitudo/leap-skill

Plugin Claude Code

Bundles 1 skill · 69 tokens together

LEAP: LLM Engineered Application Pattern. A philosophy where code is a commodity — only prompts, schemas, and tests are source of truth. AI generates all application code on demand.

not rated 6 4mo ago A tokens not measured original MIT

hub

1413

gettalon/talon-plugins

Plugin Claude Code

Bundles 1 skill · 38 tokens together

Universal channel plugin for Claude Code with 21+ platform adapters. Connect via WebSocket (default) or use built-in adapters for Telegram, Discord, Slack, WhatsApp, Signal, iMessage, IRC, Google Chat, LINE, Feishu, Matrix, Mattermost, MS Teams, and more. Full hook event forwarding, permission relay, and bidirectional.

not rated 6 5mo 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: