Subagent Isolation

Problem

If the sub-agents share one working directory, their edits race each other: one sub-agent's commit clobbers another's uncommitted changes, two sub-agents edit the same file with incompatible diffs, and a failure in one leaves the workspace in a state that breaks the others. Serialising them removes the parallelism that was the point of spawning sub-agents in the first place. Without isolated workspaces, the team has to choose between racing writes and giving up on parallel execution.

Solution

Each subagent runs in its own workspace (git worktree, container, branch, sandbox). The supervisor reconciles results back to the main workspace on completion (merge, cherry-pick, replay). Only one workspace can land changes at a time.

When to use

• A bounded sub-task has its own tool palette, prompt, or model.
• The parent's context should not bloat with the sub-agent's intermediate turns.
• Sub-agents can run in parallel and their failures must be containable.