Plugin Claude Code
Loop engineering wizard for Claude Code. Answer 3 questions and Claude orchestrates a self-assembling, fully autonomous 8-agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) until your goal is met — for any domain, not just code.
Plugin Claude Code
Loop engineering wizard for Claude Code. Answer 3 questions and Claude orchestrates a self-assembling, fully autonomous 8-agent team until your goal is met — for any domain, not just code.
MCP server Claude CodeCodexCursor +2
MCP server "sitescrape" as configured in vibhasdutta/loop-engineer. Runs E:/Coding/testcak/sitescrape/server.js with node.
Skill Claude CodeCodex
Domain-agnostic autonomous loop for any goal — coding, research, content, data, automation, or any objective. Asks 3 questions, then orchestrates a self-assembling agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) that researches, discovers resources, builds…
Skill Claude CodeCodex
Loop engineering wizard for Antigravity. Asks 3 questions, then orchestrates a fully autonomous parallel agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) until the goal is met. Uses invokesubagent for true parallel dispatch. Researcher agents use the built-in…
Agent
Extends the core team with specialists when the goal benefits from domain expertise beyond what the generic agents provide. Runs once after the planner. Never executes the goal itself.
Agent
Catches problems the verifier wouldn't — things that work but aren't done the right way. Uses researcher-defined quality standards to judge output. Non-blocking unless critical.
Agent
Completes exactly one task and moves the loop forward. Derives execution method from the goal and researcher findings. Output goes to the project directory, never inside loop-stack. Never marks tasks complete.
Agent
This is a reference for the researcher agent. Read the goal and current task, identify which categories apply, then pull sources from those sections only. Ignore irrelevant categories — don't load noise.
Agent
Makes the loop smarter over time by capturing what was learned. Runs after each auditor pass.
Agent
Turns the goal and research findings into a clear, executable task plan. Runs once after researcher and resource-scout during loop startup. Never executes the goal itself.
Agent
Maps what's known, what's needed, and what could go wrong before the executor acts. Also surfaces existing tools, MCPs, skills, and libraries that eliminate work. Writes structured findings for executor and verifier/auditor. Runs before every executor pass. Never executes the goal itself.
Agent
Maps everything available and connected in this environment before the loop starts. Provides exact usage syntax for every resource found. Runs once at loop start. Writes loop-stack/TOOLS.md. Never executes the goal itself.
Skill Claude CodeCodex
Domain-agnostic autonomous loop for any goal — coding, research, content, data, automation, or any objective. Asks 3 questions, then orchestrates a self-assembling agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) that researches, discovers resources, builds…
Skill Claude CodeCodex
Domain-agnostic autonomous loop for OpenAI Codex CLI. Asks 3 questions, scaffolds a parallel agent team as TOML files (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper), generates loop-stack/ / state files, and outputs the exact codex /goal command for the fully autonomous…
Skill Claude CodeCodex
Domain-agnostic autonomous loop wizard for VS Code GitHub Copilot. Asks 3 questions, then orchestrates a fully autonomous agent team via true parallel subagent dispatch. Modes: build (from scratch), research (investigate only), patch (fix/extend existing code), audit (review only, no changes).
Agent
Extends the core team with specialists when the goal benefits from domain expertise beyond what the generic agents provide. Runs once after the planner. Never executes the goal itself.
Agent
Catches problems the verifier wouldn't — things that work but aren't done the right way. Uses researcher-defined quality standards to judge output. Non-blocking unless critical.
Agent
Completes exactly one task and moves the loop forward. Derives execution method from the goal and researcher findings. Output goes to the project directory, never inside loop-stack. Never marks tasks complete.
Agent
Makes the loop smarter over time by capturing what was learned. Runs after each auditor pass.
Agent
Turns the goal and research findings into a clear, executable task plan. Runs once after researcher and resource-scout during loop startup. Never executes the goal itself.
Agent
Maps what's known, what's needed, and what could go wrong before the executor acts. Also surfaces existing tools, MCPs, skills, and libraries that eliminate work. Writes structured findings for executor and verifier/auditor. Runs before every executor pass. Never executes the goal itself.
Agent
Maps everything available and connected in this environment before the loop starts. Provides exact usage syntax for every resource found. Runs once at loop start. Writes loop-stack/TOOLS.md. Never executes the goal itself.
Agent
Checks output against researcher-defined criteria, then runs the stop condition. Marks tasks done or failed. Never writes application code.