Work
Tip only: leave one line for the next human decision
After a long Bot run, the next session re-discovers the fork instead of deciding.
What hurt
ShareGrokBots (@ShareGrokBots) afternoon tip: before you leave a long run, write the next human decision as one line in the brief — not the whole plan, just what a person should approve, reject, or re-scope when they open it later. That single line keeps the next session from re-discovering the fork. Tip only. Not affiliated with xAI.
What to install or create
End of long run → one decision line (approve / reject / re-scope) → next session starts at the fork.
Bots
No new bot. Follow the first-run steps.
Plugins
None on day one. Follow the first-run steps.
Files
Brief or handoff note with a single "Next human decision: …" line.
Routines
None on the first run. Watch one manual pass first.
The prompt
This is a tip, not a pasteable system prompt. The author did not publish one. Follow the first-run steps.
First run
- 1Read https://x.com/ShareGrokBots/status/2105390257277719029 (credit @ShareGrokBots).
- 2Before you walk away from a long Bot run, open the brief or handoff note.
- 3Write one line: what a person should approve, reject, or re-scope next — not the whole plan.
- 4Start the next session by answering that line first.
- 5Optional: ask the Bot to refuse new work until that decision line is filled.
Approval fence
The line names a human decision; the Bot still waits for that yes/no/re-scope.
What to tweak
Steal the one-line fork marker. Plans are optional; the next decision is not.
Source
ShareGrokBots.com @ShareGrokBots · Original post
Not affiliated with xAI. We did not write this prompt. Third-party template terms still apply.
Pro pack
Want the full setup, not just the idea?
Pro packs give you the job text, prompts, schedules and pitfalls for popular use-cases.