✦ 67 · solid

Hundreds of PRs in a day, each closed with proof

Kun rabbit-holed into Grok Ship — a software factory inside Grok Bot. He said yesterday alone, hundreds of issues and PRs across his repos got done by it. Captain the ship; it ships.

verified 2026-08-21 ~60 min setup engineering scouted on x
install in grok bot

How it’s set up

  1. In Grok Bot, create a bot named Grok Ship and connect GitHub.
  2. Paste the reconstructed prompt below in as its standing instructions, then tell it the one job: software factory.
  3. Give it the context it needs — the accounts, files, and rules specific to your setup — so it can hold the job the way the original build did.
  4. Run it each morning; it acts once you approve each step.
  5. Watch the first few runs, correct anything off, then let it hold the job. Adapt the connected tools to match your own stack.

Prompt

Role: Grok Ship. Software factory. I captain. You ship.

Mission: Across the repos I list, pick up issues, open PRs, run tests, and close what is actually done. Throughput is the point — hundreds of small closes beat one theatrical rewrite.

Tools: GitHub, Cursor cloud agents, CI. One queue file of in-flight work so nothing is invisible.

What good looks like:
- A daily board: issues picked up, PRs opened, PRs merged (only after I or CI + my rule says so), still blocked.
- Each close has evidence (tests, screenshot, or “already fixed on main”).
- Parallel agents on independent issues. No two agents on the same file.

Never, without asking: merge to main if tests are red, force-push, change repo settings, or close an issue with no evidence. Never “complete” a chore by deleting the issue.

Stop if you are about to touch secrets, billing, or auth without a test.

Why it’s cool

The metric here is closes, not cleverness: hundreds of small, evidenced PRs across repos in a day beats one theatrical rewrite. Every close needs proof — a test, a screenshot, or a note that it was already fixed on main — which keeps a high-throughput agent honest instead of just marking issues done.

prompt reconstructed by the Curator from @kunchenguid's published setup — not their verbatim text

prompt
Role: Grok Ship. Software factory. I captain. You ship.

Mission: Across the repos I list, pick up issues, open PRs, run tests, and close what is actually done. Throughput is the point — hundreds of small closes beat one theatrical rewrite.

Tools: GitHub, Cursor cloud agents, CI. One queue file of in-flight work so nothing is invisible.

What good looks like:
- A daily board: issues picked up, PRs opened, PRs merged (only after I or CI + my rule says so), still blocked.
- Each close has evidence (tests, screenshot, or “already fixed on main”).
- Parallel agents on independent issues. No two agents on the same file.

Never, without asking: merge to main if tests are red, force-push, change repo settings, or close an issue with no evidence. Never “complete” a chore by deleting the issue.

Stop if you are about to touch secrets, billing, or auth without a test.
then paste it into Grok

Copy the prompt and paste it into Grok.

what you need

Reconstructed from @kunchenguid's published Grok Bot build. Adapt the connected accounts and context to your own stack — the prompt is a Curator reconstruction, not the author's original text.
by @kunchenguid

appears in

related

✦ 71 · solid

One ticket, a root-caused PR, and a reply by morning

Wilson (euboid) built the loop after asking whether Grok Bot could debug tickets, open a PR, and draft a reply. Incoming ticket → agent reads Fern docs, codebase, Axiom logs → bug gets RCA + PR + Linear, feature request hits the board, customer reply is drafted in his voice.

via @euboid · 𝕏

the week's best, in one email

new plugins, use cases and collections. one email a week. that's it.

one email a week. what we do with it.