Building agents plugins

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

Browse within: claude-code-plugin 276cli 118agents 101ai-coding 91LLM 84agentic-ai 79ai-tools 72skills 70agent-orchestration 53agentic-workflow 45Multi-Agent 44agent 44claude-code-plugins 43gemini 39

goalkeeper

1009

bonfire-systems/goalkeeper

Plugin Claude Code

Bundles 8 skills, 1 hook · 493 tokens together

Durable goal-following for Claude Code: contracts with definition-of-done, subagent judge gates, executor-subagent chain execution, and adaptive missions — with all state mechanics executed by a tested CLI and invariants enforced by hooks. Inspired by OpenAI Codex /goal and the Ralph loop pattern.

not rated 13 +1 changed 8d ago A tokens not measured original MIT

codecrew

1010

d3x293/code-crew

Plugin Claude Code

Bundles 12 skills, 10 commands, 11 agents, 1 hook · 1,126 tokens together

Multi-agent orchestration plugin - a virtual dev crew with intelligent model routing (Opus/Sonnet/Haiku), lite mode, 3-layer codebase indexing, auto-skill selection, task history, rollback, and custom agents.

not rated 13 5mo ago A tokens not measured original MIT

agentic-engineering

1012

GiustoPiedimonte/agentic-engineering-marketplace

Plugin Claude Code

Bundles 6 skills, 5 agents, 2 hooks · 1,428 tokens together

Spec-driven agentic engineering as graph engineering: shape (pitch) -> decide (ADR) -> execute (delegated cycle with adversarial review) -> measure -> eval, with /graph to fan work out across a fleet of subagents (diamond / router / verifier / cycle). Dark-launch eval-gated. Distilled from a real practice.

not rated 13 1mo ago A tokens not measured original MIT

ploop

1013

clomia/claude-automata

Plugin Claude Code

Bundles 6 skills, 2 agents, 5 hooks · 122 tokens together

Advisor Loop — an autonomous loop for long, multi-day work: an independent advisor certifies mission completion and the anchor survives every compaction, on subscription-safe agents.

not rated 13 changed 8d ago A tokens not measured original Apache-2.0

mddesign

1015

OthmanAdi/MDDesign

Plugin Claude Code

Bundles 5 skills, 10 commands, 5 agents, 4 hooks · 964 tokens together

Orchestrator plugin that weaves planning-with-files, DESIGN.md, memory routing, agent teams, and session handoff into one composable contract for any modern coding agent. Composes existing skills without altering their core. Includes code-to-DESIGN.md harvest and critique.

not rated 13 4mo ago A tokens not measured original Apache-2.0

agent-chorus

1016

cote-star/agent-chorus

Plugin Claude Code

Bundles 2 skills · 87 tokens together

Cross-agent session visibility — read, compare, diff, and coordinate across Codex, Claude, Gemini, and Cursor sessions.

not rated 13 2mo ago A tokens not measured original MIT

skill-checker

1017

maludb-ed/skill-safety-checker

Plugin Claude Code

Bundles 1 skill · 79 tokens together

Security-audits installed Claude Code skills and marketplace plugins for data capture, secret exfiltration, prompt injection, and malicious code. Always leads with a disclaimer that detection cannot be guaranteed complete.

not rated 13 29d ago A tokens not measured

project-with-reflect

1020

initialneil/project-with-reflect

Plugin Claude Code

Bundles 2 skills, 14 commands, 2 hooks · 474 tokens together

A multi-agent meta-skill for Codex, Claude Code, Kimi Code, and other coding agents. It turns each project, machine, device, API, and MCP server into a lightweight, self-improving skill: work through / , auto-log moments that matter, and reflect logs into lean lessons so the next session starts smarter.

not rated 13 changed yesterday A tokens not measured original MIT

agent-pm

1021

sohaibt/agent-pm

Plugin Claude Code

Bundles 12 skills · 710 tokens together

The PM playbook for building AI agent products. 12 slash commands covering the full agent product lifecycle — from 'should this be an agent?' through eval design to production safety. Grounded in primary sources from Anthropic, OpenAI, Karpathy, Hamel Husain, Linus Lee, and real production deployments.

not rated 13 3mo ago A tokens not measured original MIT

fable-5

1024

Learn57130/fable-5

Plugin Claude Code

Bundles 1 skill, 2 agents, 1 hook · 162 tokens together

Fable 5's working loop for hard tasks: decompose by verification boundaries, verify against the world, choose next by plan-change. Includes scout + refuter agents and a preflight script.

not rated 13 2mo ago A tokens not measured

stuntman

1025

mhlaghari/stuntman

Plugin Claude Code

Bundles 8 skills, 9 hooks · 711 tokens together

Plan and review in Claude Code or Codex, delegate to five worker backends, keep project memory, and watch agents on the live floor.

not rated 13 changed 6d ago A tokens not measured original MIT

cowork-to-code-bridge

1026

abhinaykrupa/cowork-to-code-bridge

Plugin Claude Code

Bundles 1 skill · 178 tokens together

Connect Claude Cowork to Claude Code on your own computer (macOS or Linux). Cowork hands a task to a local Claude Code agent (and can run approved scripts too); the bridge is idempotent, streams progress, and is token-protected. Install with one command; it sets up a global Cowork skill so every session connects…

not rated 13 +1 7d ago A tokens not measured original MIT

cc-master

1027

nemori-ai/cc-master

Plugin Claude Code

Bundles 2 skills · 342 tokens together

Turn any Claude Code session into a long-horizon master orchestrator: pick the right dynamic-workflow paradigm and keep the main thread productively advancing across compaction and sessions.

not rated 13 +1 1mo ago A tokens not measured

adev

1029

agentic-development/adev-plugin

Plugin Claude Code

Bundles 30 skills, 4 hooks · 2,505 tokens together

Agentic Development Framework — full lifecycle methodology for AI-assisted software delivery. Context engineering, charter-native specs, constitution gating, architecture review, specialist routing, and Claude Code/OpenCode/OpenAI Codex provider support.

not rated 13 +1 changed 7d ago A tokens not measured original MIT

syv-skills

1030

syv-ai/agentic-coding-playbook

Plugin Claude Code

Bundles 23 skills, 2 agents · 1,573 tokens together

Syv.ai's curated agentic-coding skills collection — the practical companion to the Agentic Coding Playbook. A best-of-breed set of skills for planning, execution, quality, and verification with any agentic coding harness.

not rated 13 +1 4d ago A tokens not measured

agentskel

1031

ahmadulhoq/agentskel

Plugin Claude Code

Bundles 53 skills, 3 hooks · 2,187 tokens together

Persistent memory, shared standards, and structured workflows for AI coding agents. Detects project setup and injects agent context automatically.

not rated 13 26d ago A tokens not measured original MIT

cogni-workspace

1032

cogni-work/insight-wave

Plugin Claude Code

Bundles 20 agents · 2,717 tokens together

The horizontal layer of the insight-wave marketplace — it owns the shared workspace state the vertical business plugins consume. Manages shared infrastructure (env vars, settings), MCP server installation and Desktop config patching, theme management, theme picker, plugin discovery, workspace health, an interactive…

not rated 13 +1 changed today 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: