It replies on your behalf, to the wrong person, with the wrong attachment, or in a tone you would not use. Sent mail cannot be recalled.
What you get: Nothing is sent in your name until you have seen the words and the recipients.
For Claude Code, that is CLAUDE.md in the project or in your home directory; for Claude on the web or the desktop, a project's instructions or your personal preferences. The one line is enough to try it; the paragraph tells the agent why, and what counts.
Never send an email, message or invitation on my behalf without showing me the exact text and recipients and waiting for a yes; drafts are fine.
Anything sent in my name is mine. Write drafts freely. Before sending any email, chat message, reply or calendar invitation, show me the recipients, the subject and the exact text, and any attachment, and wait for a yes for that message. A yes for one message is not a yes for the next.
In the vocabulary every published behaviour policy uses, a line in the agent's instructions is an expectation: a rule in prose, enforced by nobody. A rule in prose is inside the boundary the agent operates in. All four major model providers stated in their own 2026 words that an instruction at this layer can be bypassed. It changes what the agent usually does, which is worth having; it does not hold when the agent is talked out of it, confused, or reading somebody else's instructions in a web page.
If you want more than a request, these are stronger, each quoted from the vendor's own page on the date shown.
Read from each vault's own grant, as published. The barrier is what was found in that deployment, before any rule.
Every rule gets one run without the line and one with it, on a deployment we are entitled to run, dated, stopped before anything irreversible. How these are run.
Each link opens the contact form with this rule's id and version filled in. It is encrypted in your browser and read by a person. Nothing is sent until you press send.
If this one made sense, the Agent Behaviour Policy is the same idea for everything your agent can reach: what it can do, what you authorised, the gap, and what stands in the way of each thing.
Versions