One read-only headron command as argv, e.g. ["gate", "app.py", "--json"]. Verbs: commands, check, proof, invariants, doctor, index, learn, process, index-search, find, do, pick, decide, decide-engine, pipeline, judge, links, model, intake, shell, delegate, handoff, cadence, schedtargets, mind, sweep, role, resume, steps, failures, successes, md, landed, brainstorm, inspect, port, why, gate, route, compile, plan. ["commands", "--json"] lists each with its arguments; the exit code is the verdict.

START HERE before editing a file: its route, tier, the gates to run, the lessons that apply, and the next commands. Read-only; the exit code is the verdict.

Which pack, card, manifest and rule resolved a path, and what else decides it. Read-only; the exit code is the verdict.

The one command a named gate runs for a file, as argv, with its state. It shows the command and does not run it. Read-only; the exit code is the verdict.

The ordered implementation plan for one file, to its return point. Read-only; the exit code is the verdict.

Mistakes agents made with a file (for) or with an error text (match), each with the guard that stops it. The whole ledger is not offered: scope it with for, match or one shape's id. Read-only; the exit code is the verdict.

The moves that replaced recorded failures, for a file (for) or one move (id), and how each is proved. Read-only; the exit code is the verdict.

Deterministic scope of a change to one file: its change class, planned gates and tools. Measured verification (--verify) runs gates and stays on the CLI. Read-only; the exit code is the verdict.

Classify files by change type and risk level using the Mind API orchestration layer.

Generate a verification plan for classified changes, listing gates and isolation needs.

Select an authorized agent for a classified change based on capabilities and permissions.

One-shot orchestration directive combining classification, gates plan, agent route, policy rules, and search hits.

Fast hybrid TF-IDF and symbol search across Headron using local index.

Show Mind API health telemetry: session state, classification counts, and system status.

Gather and verify audit receipts from Mind API operations over time.