[anupamchugh]

Real numbers from today. FastAPI codebase, ~50k LOC. 4 agents, 6 tasks, ~6 min wall clock vs ~18-20 min sequential. 24 tests, 0 file conflicts. Token cost: roughly 4x a single session.

To your cost question — agent teams are sprinters, not marathon runners. You use them for a 6-minute burst of parallel work, not all day. A 6-minute burst at 4x cost is still cheaper than 20 minutes at 1x if your time matters more than tokens.

The constraint nobody mentions: tasks must be file-disjoint. Two agents editing the same file means overwrites. Plan decomposition matters more than the agents themselves.

One thing to watch: Claude Code crashed mid-session with a React reconciler error (#23555). 4 agents + MCP servers pushes the UI past its limits.

[simianwords]

Need it be actually disjoint? Interested in learning about the limitation here because apparently the agents can coordinate.

Otherwise what’s the difference between what they are providing vs me creating two independent pull requests using agents and having an agent resolve merge conflicts?

[anupamchugh]

It does need to be disjoint. The https://code.claude.com/docs/en/agent-teams are explicit: "Two teammates editing the same file leads to overwrites. Break the work soeach teammate owns a different set of files."

locking is for task claiming — preventing two agents from grabbing the same task — not for file writes:

"Task claiming uses file locking to prevent race conditions when multiple teammates try to claim the same task simultaneously."

The coordination layer (TaskList, blockedBy, SendMessage) handles logical task sequencing, not concurrent file access. You can make agent B wait for agent A via dependencies, but that serializes the work and kills the parallelism benefit.