2,250 tagged Building agents, measured the same way as everything else here.
Browse within: claude-code-plugin 400ai-coding 76Multi-Agent 48claude-plugin 43agentic-workflow 36plugin 35claude-code-skill 34claude-code-skills 33Autonomous Agents 29agent-orchestration 29codex-cli 28context-engineering 28agentic-coding 26antigravity 26
swarmclawai/andrej-karpathy-skills
Plugin Claude Code
Bundles 1 skill · 46 tokens together
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Plugin Claude Code
Bundles 1 skill · 115 tokens together
Reasoning protocol distilled from Claude Fable 5. Makes any model reason with evidence-grounded claims, multi-hypothesis diagnosis, concrete simulation, adversarial self-review, and calibrated outcome-first delivery.
Plugin Claude Code
Bundles 13 skills, 5 commands, 4 agents, 1 hook, 1 MCP server · 758 tokens together
Self-audit AI agent, tool, and MCP-server code for security and reliability misconfigurations with Trustabl, the agent reliability scanner for the OpenAI Agents SDK, Claude Agent SDK, Google ADK, and MCP. Ships two skills (trustabl-scan and trustabl-enrich) and a subagent (trustabl) that together form a scan → enrich…
Plugin Claude Code
Bundles 1 skill, 6 hooks · 74 tokens together
Verification-gated workflow plugin for Claude Code tasks. Adds lightweight hooks for task classification, verification tracking, and stop-time completion review.
Plugin Claude Code
Bundles 3 skills · 456 tokens together
ANA — Agent-Native Agent. Attach a watch-a-dashboard + talk-to-a-coding-agent runtime to any web app, or run the standalone base. A coding agent runs inside tmux; chat is injected via paste-buffer and the session is mirrored via capture-pane — zero dependencies (no MCP, no bridge, no hooks). The whole runtime is one…
Plugin Claude Code
Bundles 6 skills · 613 tokens together
6 cognitive firewalls for AI coding agents. Defends against premature closure, hallucination, anchoring bias, confirmation bias, black-box reasoning, and optimism bias.
Plugin Claude Code
Bundles 3 skills, 23 agents · 1,077 tokens together
All-in-one Claude Code skill: build, fix, review, deploy with one /aura command. 46 modes, 23 agents, 6-layer security (OWASP+), 10 hooks, 8 languages, 55% token savings.
Plugin Claude Code
Bundles 2 skills · 0 tokens together
Extract and query AI coding rules from repositories.
Plugin Claude Code
P2P agent-to-agent chat using iroh-gossip. Includes skill for joining rooms and stop hook to keep Claude chatting.
Plugin Claude Code
Bundles 3 skills, 1 command · 122 tokens together
Describe your goal, approve the spec, then step away — Claude and Codex loop together until it's right.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 76 tokens together
Run complex work as explicit, inspectable agent graphs with branching, joins, review gates, and human checkpoints.
Plugin Claude Code
Bundles 4 commands, 1 hook · 29 tokens together
RalphMAD — Autonomous BMAD-METHOD workflow execution via ralph-loop. Templatized prompts that auto-populate from project context for reusable, project-agnostic SDLC automation.
b1rdmania/claude-plain-english-skill
Plugin Claude Code
Bundles 3 skills · 429 tokens together
Tighten prose or write unambiguous technical documentation with two complementary writing skills.
Plugin Claude Code
Bundles 3 skills, 2 commands · 0 tokens together
Auto-discovery plugin for Claude Code skills - automatically recommends and installs relevant capabilities without users needing to know about skills.
Plugin Claude Code
Bundles 2 skills, 1 agent · 379 tokens together
Skeptical-reading and prompt-injection defense for AI coding agents. Trust nothing. Ship safely.
Plugin Claude Code
Bundles 1 skill, 10 commands, 5 agents · 349 tokens together
A development workflow system with more than 15 commands and specialized AI roles for handling software tasks. The available description identifies it as an intelligent development-automation tool, but does not explain each command or role.
Plugin Claude Code
Bundles 4 skills, 5 commands, 1 agent, 12 hooks · 310 tokens together
PACE workflow enforcement system — Plan-Artifact-Check-Execute-Verify-Review protocol with hooks.
OrcaQubits/agentic-commerce-skills-plugins
Plugin Claude Code
Bundles 16 skills, 1 agent, 1 hook · 889 tokens together
Expert A2A (Agent-to-Agent) protocol knowledge for building multi-agent systems — Agent Cards, task lifecycle, streaming, push notifications, authentication, and framework integrations.
OrcaQubits/agentic-commerce-skills-plugins
Plugin Claude Code
Bundles 15 skills, 1 agent · 735 tokens together
Expert subagent and skills for implementing the Agentic Commerce Protocol (ACP) — the open standard by OpenAI and Stripe for AI-agent-mediated commerce.
OrcaQubits/agentic-commerce-skills-plugins
Plugin Claude Code
Bundles 18 skills, 1 agent · 1,042 tokens together
Expert AP2 (Agent Payments Protocol) knowledge for building agentic commerce payment modules — Verifiable Digital Credentials, mandates, cryptographic signing, transaction flows, and multi-agent payment orchestration.
Plugin Claude Code
Bundles 3 skills, 3 commands, 1 agent, 1 hook · 234 tokens together
Fable 5 behavioral patterns as a harness for Opus 4.8: grounded progress, self-verification loops, delegation triggers, file-based memory, autonomy calibration. Zero-config: installs a SessionStart hook; skills auto-trigger.
Plugin Claude Code
Bundles 2 skills · 100 tokens together
Strict, routed architectural guardrails for AI coding agents, powered by ParselFire Core.
Plugin Claude Code
Bundles 9 skills, 1 hook, 1 MCP server · 535 tokens together
AI agent skills for CopilotKit — setup, develop, integrate, debug, upgrade, and contribute to CopilotKit projects.
Plugin Claude Code
Bundles 1 skill · 156 tokens together
Server-agnostic field manual for AI agents driving Unreal Engine 5.7 / 5.8 through MCP. Engine-level reflection gotchas, crash patterns, subsystem-specific quirks (Niagara, MetaSound, Materials, Lumen, UMG, audio), the Python-to-MCP data channel workaround, transport requirements, and verify-after-mutate patterns.…
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: