Fencing Tokens

This post shows why a lease alone cannot stop a paused coding agent from overwriting another agent's work, and how fencing tokens checked at git, the database and the file system, together with a distinct FENCED error that makes the agent re-plan, prevent it.

A sub-agent's "yes, I'm prepared" can quietly evaporate the second its context gets truncated — and most orchestrators have no way to notice until two agents have already clobbered the same resource.