Distributed LLM‑agent teams can read the latest shared facts yet still act on an obsolete plan. For instance, a planner may derive an action from requirement $r_3$, another agent later commits requirement $r_4$, and an executor receives $r_4$ without replacing the plan derived from $r_3$. We call this stale‑plan execution: state freshness does not guarantee that the plan authorizing an action remains valid.\ \ We introduce PlanFence, a dependency‑scoped action‑validation protocol. Plans explicitly cite the public records they used, and an executor validates only the records that could affect the pending external action; if validation is incomplete, it replans or blocks.\ \ In 30 controlled live workflows with a post‑plan revision, a freshness‑only executor acted on the obsolete plan in every task, whereas PlanFence completed all tasks without an invalid action. Controlled replay reveals two conditional boundaries: proactive synchronization yields lower coordination stall at low churn, while PlanFence avoids repeated update‑path coordination as churn grows and avoids validating unrelated state as the shared keyspace expands. These are safety and systems‑cost results, not general task‑accuracy gains.\ \ Review