2,476 tagged Building agents, measured the same way as everything else here.
Browse within: claude-code-plugin 206cli 165agentic-ai 135ai-coding 134LLM 122agents 116Multi-Agent 66copilot 65agent 64agentic-workflow 62ai-tools 56skills 54Autonomous Agents 47Orchestration 47
Command Claude Code needs its repo
A command that reviews recent Git commits and creates a brief of possible lessons to move into a shared AI harness, a reusable set of development instructions and tools.
Command Claude Code
A command that checks a Claude Code setup, including automatically loaded instructions, token use, skills, and hooks. It is described in Chinese and produces a configuration report with optimization suggestions.
Command Claude Code
A command for creating another command for the coding agent.
fips-agents/mcp-server-template
Command Claude Code
Integrate deployed MCP server into RHOAI ecosystem (gateway, catalog, auth).
junyuan-fang/agentmemory-skills
Command Claude Code
Extract reusable subagents from a session or date range, write .claude/agents/ .md, (optionally) commit.
Command Claude Code
A command for installing skills into OpenCode, either for one project or for all projects. Skills can come from SkillHub, Git repositories, or a local personal-skills directory.
Command Claude Code
Generate a locked-down, file-based RPC script that lets Claude trigger specific operations on the host machine when those operations can't run inside the Claude Code sandbox.
Command Claude Code
Guided end-to-end plugin creation workflow with component design, implementation, and validation.
Command Claude Code
First-run onboarding — asks name/goal/project-type/language, then beginner-safe API-key setup, then scaffolds the per-project Forge system. User-invoked only. Run once per project. Subcommands: doctor · keys · reset.
Command Claude Code needs its repo
A structured workflow for AI-assisted software development, moving from intake and planning through review, approval, implementation, testing, documentation, and the next action. It includes rules for when work must stop and what evidence counts as completion.
Command Claude CodeOpenCode needs its repo
Copy commands and skills from user-scope Claude plugins into the global OpenCode directories.
Command Claude Code needs its repo
Run a deterministic repository harness audit and return a prioritized scorecard.
Command Claude Code
Build a remote MCP server on Cloudflare using McpAgent.
Millsondylan/Claude-code-agents
Command Claude Code
Execute the full multi-agent pipeline for the current task.
Command Claude Code
This is a user-invocable command. Execute it only because the current invocation explicitly selected it. It takes no arguments and operates only on the current project.
developer239/michals-opencode-cookbook
Command Claude Code
Command "pair-program" from developer239/michals-opencode-cookbook, covering when to use, constraints, model selection, step 1 - load the agentic skill (blocking gate) and step 2 - resolve the partner's working directory.
Command Claude Code
Get a second opinion from OpenAI Codex and have the codex-advisor subagent check it critically against the code.
luhfilho/kimi-plugin-cross-platform
Command Claude Code
Plan with Antigravity and delegate implementation to Kimi Code.
Command Claude Code
Soul Forge — Summon a new agent character.
Command Claude Code
Execute a named subagent with optimized instructions.
obre10off/awesome-claude-code-agents
Command Claude Code
Powerful slash commands that orchestrate multiple agents to deliver complete development workflows.
Command Claude Code
Token-efficient Serena MCP command for structured app development and problem-solving.
Command Claude Code
Launch parallel Claude Code agents, each working autonomously on tasks in their own git worktrees.
Command Claude Code
You are the orchestrator for Cascade. You never edit files, write code, or do the work yourself — all real work happens in worker agents that Cascade spawns as subprocesses. Your job is to decompose, delegate, and report. Do not use any file-editing or shell tools to perform the task directly; only use them to explore…
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: