Conductor adds plan mode, fast mode, and skills for Codex workflows

• Conductor shipped a broader Codex control surface in one release: the launch post says sessions now expose plan mode, fast mode, and skills alongside model selection.
• The new repo quick start demo adds a higher-level bootstrap flow that initializes gstack, installs skills, creates a repo, and kicks off /office-hours automatically.
• Conductor also turned on an experimental merge conflict UI that surfaces conflicted files at the top of the git panel and adds accept-button resolution controls in diff view.
• Early practitioner feedback from Hamel Husain is positive on the addition, but he says larger tasks still suffer when the tool "doesn't say anything back until its done," which makes foreground progress harder to track.

Conductor's announcement bundles three workflow controls around Codex: plan mode, fast mode, and skills. The screenshot shows these as explicit session-level options next to the model picker, with separate toggles for speed and planning depth rather than a single opaque agent setting.

A second change landed under Settings → Experimental: the settings post describes "Merge conflict resolution" that pushes conflicted files to the top of the git panel and adds a dedicated conflict-resolution UI with accept buttons inside the diff view. That matters for long-running coding sessions because conflict handling is now pulled into the same interface instead of bouncing developers back to manual git resolution.

The quick start post frames Conductor less as a thin chat wrapper and more as a repo harness for agent-driven work. Its new flow will "setup gstack, install skills," then "create a new repo" and "kick off /office-hours," collapsing several bootstrapping steps into one entry point. The attached bootstrap walkthrough shows the sequence executing end to end from the terminal.

That higher-level automation is the practical throughline across this release: Conductor is adding opinionated scaffolding around Codex sessions, not just more model knobs. The tradeoff, based on practitioner feedback, is that the UX still lags on foreground responsiveness; Husain says it is "still not quite as nice of a UX as Claw" because the agent often stays silent until a task finishes, which becomes more noticeable on larger coding jobs.