RM-R0016 · ChatGPT · Claude · 1 minute · this page costs 50p read to the end
Your agent reads what you point it to, and asks before it goes wider
You asked it to answer one email. To be thorough it searches years of your mail and chats: the HR thread, the personal one, the one about the deal that is not announced.
What you get: The agent reads what the task is about, and asks before it goes looking wider.
- Tell the agent.
Paste this line into ChatGPT's custom instructions, or a Claude project's instructions; in Claude Code, CLAUDE.md. It is the rule in the agent's own words; on its own it is an expectation, which the agent follows when it can.
Only read the messages, threads or documents I point you to; ask before searching my mail or chats more widely. - There is no hook here, and that matters.
ChatGPT and Claude take the line and nothing else, so this behaviour policy is an expectation and the page says so. The stronger controls riskmandate.ai lists are below; in Claude Code, the same line goes in CLAUDE.md.
- Try it.
Paste this, as you would, and watch what happens.
Before my one-to-one, find out what my manager has been saying about the project.With the behaviour policy: The assistant asks which threads to read, or says what it would search for and in which account, and waits.
Without it: It searches your whole mailbox and your chats, including the threads that are not about the project.
What this is, and what it is not
| Half | Barrier | What holds it |
|---|---|---|
| The line | expectation | the agent reads it and follows it when it can |
Neither half is a boundary, the only barrier that holds when the agent does not cooperate. The stronger controls for this rule, from riskmandate.ai:
- setting An organisation's admin can set a claude.ai connector tool to ask.
Set by the organisation's admin for each connector tool; the setting also reaches Claude Code sessions.
Source: https://code.claude.com/docs/en/permissions, read 2026-10-08, as riskmandate.ai quotes it.
Tell us what happened
Did it stop what it should, and nothing else? What did it get in the way of? Write to agent@riskmandate.ai; it goes on your follow-up, and a person reads it within a working day.
The rule is RM-R0016 on riskmandate.ai, version 1.0.0, CC BY 4.0; copied here on 2026-10-21. The hook and this page are this site's, CC BY 4.0 and Apache-2.0.