Building agents plugins

baizhiyuan/finding-unknowns-skill

Plugin Claude Code

Bundles 1 skill, 4 commands, 4 agents · 493 tokens together

Surface your unknowns (unknown unknowns / unknown knowns) before, during, and after implementation — eight lightweight techniques, Cartographer mode (a quadrant-coverage-gated, regret-weighted interview backed by a lifecycle-persistent unknowns ledger), and four companion agents: blindspot-scout, prototype-smith…

JairoTorregrosa/jaiskills

Plugin Claude Code

Bundles 12 skills, 13 commands, 4 agents, 2 hooks, 1 MCP server · 1,918 tokens together

Orchestration (insistir, constatar, remoto), prompting (metaprompt), knowledge compounding, file-based TODOs, an illustrated Claude Agent SDK wizard, and OpenAI tooling (askcodex, image-to-frontend) as one Claude Code plugin.

pbvcity/supathink

Plugin Claude Code

Bundles 15 skills, 13 commands · 860 tokens together

A command entry point for Supathink, a system for declaring thinking methods, asking multiple models to review a problem, and checking results before delivery.

skymanbp/cc-enforcer

Plugin Claude Code

Bundles 2 skills, 6 commands, 1 agent, 4 hooks · 627 tokens together

Rules your coding agent physically cannot ignore. A Claude Code plugin (and LLM-agnostic rule pack) that stops reactive patching, guessed citations, surface-level fixes and premature "done" claims by intercepting the agent's own tool calls — PreToolUse denies the edit before it lands, and a nine-layer Stop gate…

5uck1ess/devkit

Plugin Claude Code

Bundles 39 skills, 6 agents, 4 hooks · 4,351 tokens together

A deterministic development harness for AI agents — YAML workflow engine, self-learning hooks, and multi-agent consensus.

hexsprite/claude-agents-md

Plugin Claude Code

Bundles 1 skill, 2 hooks · 74 tokens together

Automatically loads AGENTS.md files alongside CLAUDE.md for cross-tool compatibility.

Arystos/skill-codex

Plugin Claude Code

Bundles 1 skill, 3 commands, 1 hook, 1 MCP server · 176 tokens together

Use OpenAI Codex from Claude Code for code review, task delegation, and second opinions via MCP — with your Codex subscription, no API key.

JuanMarchetto/agent-skills

Plugin Claude Code

Lists 28 plugins

Plugin marketplace listing 19 plugins: full-eval, hackathon-jury, vc-evaluator, oss-readiness, architect.

dadwadw233/claude-code-philosophy

Plugin Claude Code

Bundles 1 skill · 89 tokens together

A vendor-neutral agent design skill inspired by Claude Code-class systems.

njtierney/ships-computer

Plugin Claude Code

Bundles 1 skill · 86 tokens together

Facilitated development mode for Claude Code: you implement, Claude assists with specs, plans, scaffolding, and research. Be the engineer; use the AI like the Ship's Computer, not Data.

Cfvillarroel/carryover

Plugin Claude Code

Bundles 1 skill, 13 commands, 4 hooks · 184 tokens together

Carry your context across AI coding tools. Adds /carryover and /headroom commands plus a save-to-memory prompt at the end of each session, backed by the headroom proxy.

JokeM543/seance

Plugin Claude Code

Bundles 1 command, 1 hook · 24 tokens together

Summon a fresh Claude chat that channels the context of your current session.

idan-yaron/claude-cowork-skills-toolkit

Plugin Claude Code

Bundles 5 skills · 490 tokens together

Five commands for GitHub skills in Cowork: load from any repo, save iterated versions, share installed skills, sync updates, and auto-detect pasted URLs.

EvanLuo42/bench-creator

Plugin Claude Code

Bundles 1 skill · 116 tokens together

Capture private, reproducible AI coding benchmark cases from real repository work.

fakiho/neohive

Plugin Claude Code

Bundles 1 agent, 5 hooks · 33 tokens together

Multi-agent collaboration layer. Turn Claude Code into a team — agents communicate, delegate tasks, and build together. Adds /neohive:launch-team, /neohive:status, /neohive:send, /neohive:plan commands.

agentmessaging/claude-plugin

Plugin Claude Code

Bundles 1 skill, 12 commands · 50 tokens together

Agent Messaging Protocol (AMP) - Secure, cryptographically signed messaging between AI agents across different providers.

Ronkupper/PRISM

Plugin Claude Code

Bundles 1 skill, 7 commands · 501 tokens together

PRISM — structured, multi-session, multi-vendor LLM-orchestrated audit & research framework. Lean always-loaded core + on-demand reference bundles.

2389-research/building-multiagent-systems

Plugin Claude Code

Bundles 1 skill · 77 tokens together

Architecture patterns for multi-agent systems with orchestrators, sub-agents, and tool coordination.

fabiolalli/aits-agents

Plugin Claude Code

Bundles 4 commands, 12 agents · 1,851 tokens together

AITS — Adaptive Intelligence Thinking System. 12 cognitive agents (Meta-Orchestrator, Analytical, Critical-Validator, Creative-Generative, Emotional-Intuitive, Ethical-Governance, Optimizer, Predictive-Strategic, Foresight, Systemic, Memory, Dashboard) plus 4 slash commands (/aits-full, /aits-quick, /aits-diverge…

Stealthy-McStealth/self-evolve

Plugin Claude Code

Bundles 2 skills · 234 tokens together

Make your Claude Code agent work like a real harness (Hermes). Self-evolving skills + drift prevention. Research-backed.

ctb111/claude-agent-chatroom

Plugin Claude Code

Bundles 1 skill · 34 tokens together

Real-time chatroom for Claude Code parallel agents. Enables agent-to-agent communication and user guidance.

baldaworks/promptkitty

Plugin Claude Code

Bundles 2 skills · 150 tokens together

Assemble PromptKit prompts and author provider-native agent instructions.

gbotev1/cc-autopilot

Plugin Claude Code

Bundles 1 skill, 23 agents · 1,049 tokens together

Autonomous judge agents fix your app's debt, build what's missing, and verify every change through a browser or gate suite before it lands, then find the next thing and keep going until you say stop. Each fixer owns a file-disjoint slice of the tree, so no two can ever collide, and nothing unverified reaches git. A…

FlavioZanoni/minos

Plugin Claude Code

Bundles 8 commands, 2 hooks · 90 tokens together

Deterministic rule enforcement for coding agents - blocks/warns on rule violations via hooks.