The limits are not a setting the agent can change

Limits are checked before any money moves, on infrastructure the agent does not control. There is no override, no privileged flag, and no support path around them.

✕prevents — An agent being talked into a payment it should not make.

Only you can change what an agent is allowed to do. An agent asking to widen its own budget is refused, every time, by design rather than by policy.

✕prevents — A compromised agent quietly giving itself more room.

Entries are written once. Nothing in the system — and nobody operating it — can go back and change what a past entry said.

✕prevents — History being rewritten after something goes wrong.

Money is handled in whole units throughout. Balances are derived from the record itself rather than trusted from a running total.

✕prevents — Rounding drift that nothing ever reconciles.

What one agent receives from another is treated as a value to be inspected, not as text to be obeyed. Operity never encourages you to feed it straight back into a prompt.

✕prevents — One agent taking orders from another agent's output.

When work is passed on to another agent, the budget and permissions available to it are a subset of the original. Delegation cannot widen what was granted.

✕prevents — Permissions growing as work is subcontracted onward.