Building agents commands

2,432 tagged Building agents, measured the same way as everything else here.

Browse within: claude-code-plugin 215cli 154ai-coding 126agents 123agentic-ai 122LLM 117Multi-Agent 68agentic-workflow 64copilot 64agent 63ai-tools 57skills 55Autonomous Agents 48Orchestration 47

ralph_done_v2

121

ahostbr/kuroryuu-public

Command Claude Code

Signal task completion to Ralph leader (V2 with verification discipline).

not rated 12 4mo ago A 13 tokens AGPL-3.0

kit-research

123

ezBuilder/code-brain

Command Claude Code

Research Claude Code and Codex CLI changes before modifying this kit.

not rated 11 8d ago A 0 tokens original Apache-2.0

swarm

126

liortesta/ClawdAgent

Command Claude Code

Launch a coordinated multi-agent team with a shared task board and Leader→Workers pattern.

not rated 11 11d ago A 0 tokens original Apache-2.0

codex-worker

127

cklxx/elephant.ai

Command Claude Code

Activate the Codex worker protocol defined in CLAUDE.md § "Codex worker protocol (Brain + Hands)".

not rated 11 5mo ago A 0 tokens original MIT

list-agents

128

jkrandom-sudo/opencode-plugin-peers

Command Claude Code

List same-machine opencode peers you can exchange messages with (alias of /peers, compatible with Claude Code's /list-agents).

not rated 11 +1 10d ago A 28 tokens original MIT

self-improve

129

pedrol-cmd/brain-drin

Command Claude Code

Auto-otimização com filtro de qualidade — só o que prova valor entra, tudo que não performa sai.

not rated 11 4mo ago A 23 tokens original MIT

bridge-monitor

130

victorzhong0110/skill-evolution

Command Claude Code needs its repo

You are a bridge monitor for the skill-evolution framework. Your job is to process LLM completion requests that the Python framework writes to a bridge directory, using Agent sub-tasks with clean context.

not rated 10 8d ago A 0 tokens original MIT

ralph

131

T-0-co/t-0-spec-kit-ralph

Command Claude Code

Run Ralph Wiggum Loop on a spec to execute tasks autonomously.

not rated 10 2mo ago A 14 tokens original MIT

autoresearch

132

Maleick/AutoResearch

Command Claude Code

Run a subagent-first structured improve-verify loop in OpenCode.

not rated 10 1mo ago A 0 tokens original MIT

crystallize

133

axiomantic/spellbook

Command Claude Code

Transform verbose SOPs into high-performance agentic prompts via principled compression. Use when user says "/crystallize", "compress this prompt", "make this more agentic".

not rated 10 4d ago A 36 tokens original MIT

commands

134

CGSOG-JumpStarts/JumpStart-AutoNav

Command Claude Code

This file defines the slash commands that drive the Jump Start workflow. Each command activates a specific agent or system function. These definitions are consumed by the AI assistant integration layer to route commands to the correct agent persona and instructions.

not rated 10 3mo ago A 0 tokens original MIT

squadai-init

135

PedroMosquera/squadai

Command Claude Code

You are running the squadai squadai-init routine: read the current repository, understand what it actually contains, and refine each configured agent's role files (or solo instructions file) so they are tuned to this codebase — without losing any methodology semantics squadai installed.

not rated 8 1mo ago A 0 tokens original MIT

graphstack

136

MertCapkin/GraphStack

Command Claude CodeCursor

Graph-first, automatically orchestrated AI development workflow. One prompt starts the entire lifecycle — from blank repo to production.

not rated 8 2mo ago A 0 tokens original MIT

superpowers

137

naimkatiman/continuous-improvement

Command Claude Code needs its repo

Law activator and dispatcher — route the task to the right Law-aligned specialist across continuous-improvement and four vendored upstream skill libraries (Obra superpowers, addy-agent-skills, ruflo-swarm, oh-my-claudecode).

not rated 7 changed yesterday A 55 tokens original MIT

implement

138

steve-magne/hookstack

Command Claude Code

Conçoit (si user-facing) puis livre une feature, selon le pattern à 3 rôles séparés (anti-biais d'auto-éval). Deux sources d'entrée — le mode est déduit de l'argument .

not rated 7 5d ago A 0 tokens original MIT

orchestrate

139

MN-Lizard-Team/aiyu-multi-agent

Command Claude CodeCursor needs its repo

You MUST start your FIRST response with this exact agent activation line.

not rated 7 3mo ago A 0 tokens original Apache-2.0

rapp

140

microsoft/aibast-agents-library

Command Claude Code ✓ vendor

You are now in RAPP Pipeline mode. Help the user build an AI agent from discovery to deployment using the unified RAPP agent.

not rated 7 yesterday A 0 tokens original MIT

build-mcp

142

runlayer/plugins

Command Claude Code

Build, test, and optionally deploy an MCP server.

not rated 7 +1 6mo ago A 14 tokens

mint-agent

143

POWERFULMOVES/PMOVES.AI

Command Claude Code

Mint a new PMOVES agent through Archon's factory — scaffold persona doc, register form, assign room, emit NATS mint event.

not rated 7 today A 28 tokens

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: