Grokbot TemplatesGrokbot Templates
All use cases

Work

Routine reliability audit: six checks before you change anything

You notice a routine was idling or doing the wrong thing only after the week's usage is gone.

Share

What hurt

@stansKoya tip (adapted from @Michael_Fenech_'s six-check idea): before you retune live schedules, run a ROUTINE RELIABILITY AUDIT. Each bot reports its routines; check unique owner, time/timezone/frequency, fresh inputs, what success looks like and where it lands, whether approval steps can go stale, and how missing info / disconnects / low quota are reported. Then pick the top three for a safe test plan — no live changes or dry-runs without approval (dry-runs still do real work and burn usage). Distinct from usage-auditor-holes-baseline (different six checks focused on routine reliability). Author-quoted Chinese prompt (EN translated). Not affiliated with xAI.

What to install or create

Paste audit prompt → each bot reports routines → six checks → top-three safe test plan → approve before any change or dry-run.

Bots

  • No new bot. Follow the first-run steps.

Plugins

  • None on day one. Follow the first-run steps.

Routines

  • None on the first run. Watch one manual pass first.

The prompt

Routine reliability audit — six checks, change nothing without approval (author-quoted)

Quoted from @stansKoya (adapted from @Michael_Fenech_) — as published. Do not invent a second system prompt.

Last line is our approval fence: Never send, post, spend, or buy without my explicit yes.

(Translated from the author's Chinese.)

Run a ROUTINE RELIABILITY AUDIT on my Grok Bot team. Have every Bot report its own routines. Check each one for: 1) whether there is a single owner; 2) whether time / timezone / frequency are sensible; 3) whether inputs use the latest sources; 4) what success looks like and where it is delivered; 5) whether steps that need my approval can go stale; 6) how missing info / disconnects / low usage quota are reported. Pick the three most important items and give me a safe test plan. Do not change or dry-run any live routine without approval — a dry-run still does real work and burns usage.

Never send, post, spend, or buy without my explicit yes.

First run

  1. 1Read https://x.com/stansKoya/status/2118145047325794655 (credit @stansKoya; six-check idea also @Michael_Fenech_).
  2. 2Paste the author ROUTINE RELIABILITY AUDIT prompt into your lead bot; require a report only.
  3. 3Review the six checks per routine: unique owner, schedule/timezone, fresh inputs, success shape + destination, stale approval steps, failure reporting.
  4. 4Approve a safe test plan for the top three findings only.
  5. 5Change or dry-run nothing live until you say yes — dry-runs still burn usage.

Approval fence

Report only first — never change, pause, or dry-run a live routine without your yes.

What to tweak

Steal the six reliability checks; report first, don't burn usage on unapproved dry-runs.

Source

Stans @stansKoya · Original post

Not affiliated with xAI. We did not write this prompt. Third-party template terms still apply.

Browse templates

Browse team blueprints

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.

See Pro