Building agents plugins

3,758 tagged Building agents, measured the same way as everything else here.

Browse within: claude-code-plugin 276cli 122agents 96LLM 87ai-coding 87agentic-ai 77ai-tools 70skills 70agent-orchestration 53agentic-workflow 46agent 43claude-code-plugins 43Multi-Agent 42gemini 39

effort-router

2305

arpan1221/claude-effort-router

Plugin Claude Code

Bundles 1 skill, 2 hooks · 65 tokens together

Routes each turn to an effort level based on your real Claude subscription usage limits — go deep while budget is cheap, conserve as it runs down.

not rated 2 1mo ago A tokens not measured original MIT

project-builder

2307

enzoterra/claude-project-builder

Plugin Claude Code

Bundles 3 skills, 8 agents · 904 tokens together

Pipeline de skills e subagentes que conduz qualquer projeto de software (fullstack, API, CLI, biblioteca, dados/IA) do brainstorming ao código executável: analista e desenvolvedor de ideias, escritor de plano, designer, devs backend/banco/frontend/IA, analista de infra e analista de segurança — todos seniores, com…

not rated 2 2mo ago A tokens not measured AGPL-3.0

cursor

2308

ningzio/cursor-plugin-cc

Plugin Claude Code

Bundles 1 skill, 6 commands, 1 agent, 2 hooks · 116 tokens together

Dispatch tasks to cursor-agent from Claude Code. In-place by default; --isolated opts into a sandbox worktree. Background jobs, session boundary safety, structured policy refusals.

not rated 2 4mo ago A tokens not measured original MIT

harness-claude

2309

vasuag09/harness-claude

Plugin Claude Code

Bundles 32 skills, 8 agents, 6 hooks, 3 MCP servers · 2,763 tokens together

Lean full-SDLC Claude Code harness — Discover, Plan, Implement, Verify, Maintain — with anti-rationalization guards on the gate skills, portable skills (installable anywhere via the skills CLI), researched git conventions (branch-at-first-write, Conventional Commits, detect-and-follow), always-on pipeline routing, a…

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

dev

2310

0xTimepunk/archon

Plugin Claude Code

Bundles 1 skill, 2 commands · 75 tokens together

General-purpose spec-driven development plugin. /dev:spec creates specs via AI interview + research. /dev:work executes specs using adaptive agent teams.

not rated 2 5mo ago A tokens not measured

third-party

2312

maslenkov/cc-third-party

Plugin Claude Code

Bundles 4 skills · 165 tokens together

Tools for installing and security-auditing plugins, skill sets, and modules from local sources.

not rated 2 4mo ago A tokens not measured

claude-router

2314

mpandzo/claude-router

Plugin Claude Code

Bundles 1 skill, 2 hooks · 0 tokens together

Model-tier router: on agent spawns, an LLM classifies the brief and injects a cost-appropriate Claude model (Haiku/Sonnet/Opus) via a PreToolUse hook (Anthropic API, or claude -p fallback). Also ships a model-router skill.

not rated 2 1mo ago A tokens not measured

cc-loadout

2317

XBlueSky/cc-loadout

Plugin Claude Code

Bundles 4 skills, 2 hooks · 489 tokens together

Guided Claude Code profile creation plus multi-account switching. Bundles the /cc-loadout:init skill; the cc-loadout CLI does the discovery and writing.

not rated 2 changed 7d ago A tokens not measured original MIT

llm-tools

2318

yehosef/llm-tools

Plugin Claude Code

Bundles 1 skill · 94 tokens together

Multi-model LLM orchestration - route tasks to the right model, run in parallel, synthesize results.

not rated 2 1mo ago A tokens not measured

pixl-crew

2319

hamzaPixl/pixl-ai

Plugin Claude Code

Bundles 93 skills, 14 agents, 6 hooks · 10,342 tokens together

Multi-agent development crew: 14 specialized agents, 93 skills (including caveman token-compression suite), studio templates, and companion plugins (LSP, Trail of Bits security, playground). Full-stack TypeScript, Python, and Swift with DDD patterns, CI/CD pipelines, design extraction, and cross-session memory.

not rated 2 5mo ago A tokens not measured original MIT

progress-observability

2321

observability-oss/progress-observability-plugin

Plugin Claude Code

Bundles 7 skills, 8 commands, 1 MCP server · 803 tokens together

Observe, debug, cost-manage, and evaluate AI systems from the Progress Observability Platform: an instrumenter that retrofits observability onto an existing Python, TypeScript, or .NET agent and verifies traces arrive, a scaffolder for new instrumented .NET agents, a setup health check, then trace triage, cost/usage…

not rated 2 2d ago A tokens not measured original MIT

fable-sol-fusion

2322

Rylaa/fable-GPT-5.6-fusion

Plugin Claude Code

Bundles 1 skill, 2 commands · 351 tokens together

Multi-model fusion for Claude Code + Codex: a parallel panel (1x Claude Fable 5 via claude -p locked at --effort max + 1x GPT-5.6 Sol via codex locked at ultra; /fusion-max adds a 2nd Fable 5 panelist) answers a task independently and blind, then GPT-5.6 Sol (codex, ultra) judges and a Claude Fable 5 synthesizer (via.

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

factory

2324

genai-jerry/claude-software-factory

Plugin Claude Code

Bundles 6 skills, 19 commands, 1 hook · 604 tokens together

An agent-driven software factory: GitHub issues carry pipeline state, OpenSpec change folders carry spec content, ten agent roles move work between them behind four approval gates, with releases gated on GitHub milestones.

not rated 2 4d ago A tokens not measured original MIT

dev-plugin

2325

liaogui1023/coding-plugin

Plugin Claude Code

Bundles 4 skills · 182 tokens together

A development plugin containing tools for project documentation, creating skills, managing pull requests, and advanced search.

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

comp4020

2327

comp4020-agentic-coding-studio/core

Plugin Claude Code

Bundles 11 skills · 1,091 tokens together

Skills for COMP4020/COMP8020 Agentic Coding Studio students: setting up the course environment, tracking budget and deadlines, and getting each week's deliverable started, checked and shipped. Ships no hooks; the optional status line lives in the companion comp4020-statusline plugin.

not rated 2 changed 4d ago A tokens not measured

icm

2328

andyrids/icm-spec

Plugin Claude Code

Bundles 7 skills, 1 agent, 5 hooks · 209 tokens together

Interpretable Context Methodology - workspace pipelines, spec-driven artifacts and hook-enforced gates.

not rated 2 25d ago A tokens not measured original Apache-2.0

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: