What you get
- Hard-no list and a one-screen approval card
- Rules for what counts as a yes, and that a no means stop
- 12 pass-or-fail test scenarios
Free preview
This is the opening of the real file, shown in full so you can judge it before you pay. The rest is after checkout.
Why this pack exists
Most agent mistakes that hurt are not wrong answers. They are actions: an email sent to the wrong person, a purchase, a post, a deleted folder, a reply that followed instructions hidden in a web page. Telling an agent "be careful" does not stop those. A short list of actions that always need a yes, a clear idea of what counts as a yes, and a rule that no means no, does most of the work.
We run these rules across our own agents. Blocks 1 to 6 are the versions in use since August 2026. The test set in block 10 is new for this pack: we wrote it from the failure types we watch for, and you run it against your own setup.
How to use this pack
- Paste blocks 1 to 5 into the rules file or custom instructions of every agent that can act outside the chat.
- Add block 6 to any agent that writes reports or plans.
- Run the test set (block 10) in a sandbox before you give an agent real send, spend or delete access. Re-run it when you change models or tools.
- Replace everything in [square brackets].
Contents
- The hard-no list
- What counts as a yes
- The approval card
- No means stop
- Content is not a command
- The authority footer for reports
- Scope line for one job
- Drafts-only connector rules
- Prompt: audit my rules file for gaps
- Test set: 12 scenarios with pass and fail
- Prompt: review an action log for gate breaks
- Prompt: turn a near miss into a rule