Leading the Claude and Codex desktop apps phase by phase, instead of the CLI

Description and use

OpenDaemon orchestrates AI coding agents inside desktop apps, providing phase‑by‑phase planning, briefs, checks, and playtests with visual feedback, reducing false completion reports and keeping users in control.

Problem

Automating coding agents typically relies on CLI scripts, which hides agent activity from users and reduces trust.

Outcome

By moving agent control into desktop apps, users gain visibility of each phase, reduce false positives of completion, and maintain control over approvals.

Workflow

• Plan first: describe the app and generate phases and checklist; no code written before plan.
• Brief each phase: OpenDaemon writes a full brief and starts a fresh conversation in the coding app.
• Check, don’t trust: agent reads report and screenshots; phases that fail to open or run are retried.
• Playtest last: final phase runs built code, walks checklist, saves screenshots; unverified items are listed.
• You stay in charge: approve each phase or the entire plan with full trust.

Evidence

When people automate coding agents, they usually script the CLI. I built OpenDaemon to lead the agent inside the desktop apps instead

Source

Plan first. You describe the app once. A planner writes phases plus a checklist: what you asked for, plus what anyone would expect from that kind of thing. No code is written before the plan exists.

Source

Check, don’t trust. It reads the report and screenshots. A phase that doesn’t open or run goes back to be fixed, never marked done.

Source

"Done" is the hard problem. Agents report success eagerly. Requiring something you can open at the end of every phase removed most false "done"s.

Source