✦ Matthias Ewald DE

AI · Developer tooling / AI coding agents

AgentAutoSetup

A Windows-first scaffolder that turns any folder into a repository ready for AI coding agents: an agent manual, safety rules that are enforced rather than just written down, git hooks and verification gates from day one, all in one wizard run.

2026 developer tool
Python Node.js PowerShell Git hooks
The agent arcade in demo mode: an open-plan office floor where six AI agents appear as robots at their desks, with a library, notice board, gate wall and shipping dock, and agent cards below The agent arcade in its light theme: robots on the office floor, and below it the message dock with the agents' reports as formatted text Session overview report: 3 sessions and 15 subagents, with totals for API turns, tool calls and output tokens, and a sortable table of every session and subagent with model, branches, active minutes and tool calls Task report: 33 task docs and 98 owed checks, with totals for open designs, delivered work, audits and outstanding items, and a table of design docs with their status and last change
Role
Author, developer & owner
Platform
Windows · GUI wizard, console, standalone exe
Agents
Claude Code · GitHub Copilot · OpenCode
Workflow
AI-assisted, agent-driven

Overview

Point it at a folder, new or existing, and a live preview shows exactly what will be written and what will be left alone before anything happens. Three guarantees hold on every run: existing files are never overwritten, an existing repository is never committed to, and nothing is installed without an explicit yes. All supported agents share one set of rules, so they cannot drift apart.

Rules that hold

Written instructions alone are not enough. Measured across real session transcripts, the patterns an agent was told never to use were used more after the rule went into its manual. So every rule lives in the strongest layer that can hold it:

  • A guard hook checks each command an agent runs against a rule table: “never” rules are refused with the replacement named, “ask first” rules prompt the user
  • A line-ending normaliser keeps every file an agent writes consistent
  • Verification gates (instruction lint, Python checks, doc links, import cycles and more) run before every push, reporting every failure at once
  • Compaction hooks carry an agent’s branch, task and state across a context compaction

Watching the agents work

An optional agent arcade draws every live session, coordinator and subagent as a robot on an open-plan office floor: a desk per agent, zones they walk to for their current tool, context bars, a message dock with what each agent said, a git graph of what their branches did, and a replay mode for past sessions.

More

  • Optional extras: a Vite + TypeScript toolchain, Playwright browser testing, Godot support and a fast merge lane for prototyping
  • Audit mode reports how an existing project differs from the current template, read-only
  • Session stats show per session and per agent what was done: tool calls, files, time and tokens
Three minutes of the agent arcade in demo mode: agents moving between the stations while their reports arrive in the message dock
← All projects