hexum_control_status
Last updated 12 September 2026
When to call
When the agent is repeating edits or failing the same check.
Arguments
No arguments. Uses the current MCP session.
What comes back
Drift score, health, churn, suggested forbid lines.
What the agent does next
If stuck_in_loop, write the patch before more edits.
All five tools: Hexum MCP tools. Contract file: architecture.hexum.
FAQ
What is hexum_control_status?
Reports healthy, drifting, or stuck_in_loop. Pair with hexum_control_synthesize to get forbid lines and SKILL.md directives. Live session lists on /app require sign-in; they never include another user's sessions.
When should the agent call hexum_control_status?
When the agent is repeating edits or failing the same check.
Does Hexum replace Cursor or Claude Code?
No. You keep Cursor, Claude Code, Antigravity, Codex, or Grok. Hexum is not an editor and not a model. You paste a key into the agent you already use.
Does the architecture check use an AI?
No. It reads a rules file in your repo and reports forbidden imports. It does not call a model, so it does not guess.
Does Hexum store my repo?
No. We do not keep the code your agent sends. We do not train on it. Policy: /zdr.