End-to-end feature/bug-sweep workflow for aitm — understand, reproduce against a real run, explore and build with a hive of parallel agents in this one checkout (never worktrees), path-disjoint slices, verify under Bun AND Node, PR, merge, and (only when asked) release to npm. Tracks in GitHub issues. Reads intent…
End-to-end bug-fix workflow for aitm — root-cause in depth from a description or log, fix with a regression test, sweep for the same bug family, verify under Bun + Node, PR, merge on green with comments handled, release to npm when asked.
Named provider profiles — bundle the provider triple (API key + base URL + per-tier models) under a name and switch the whole provider in one command, version-manager style (think nvm use). Profiles live in the global config file /.aitm.json under profiles, with activeProfile naming the one in effect.
Manual self-update. Reinstalls the published @developerz.ai/aitm package globally — nothing ever updates automatically; the command only acts when you run it.
End-to-end feature/bug-sweep workflow for ui-debugger-mcp — understand, reproduce against a real target, explore in parallel, split into path-disjoint slices, build with a hive of agents in this ONE checkout (never worktrees), gate green, PR, merge, release to npm. Tracks in GitHub issues. Reads intent from the prompt.
Claude Code instructions for developerz-ai/ui-debugger-mcp, covering ui debugger mcp, response rules, what this is, reference repos (read for patterns, don't copy blind) and architecture.
How to drive claude (Claude Code) as a non-interactive CLI tool — headless runs, MCP servers, permissions, output formats, and piping. Use when scripting Claude, spawning a sub-agent from another process, or wiring Claude into CI/automation.
Claude Code instructions for developerz-ai/ai-gaming-agent-mcp, covering claude.md, project overview, architecture, project structure and key commands.