deploy-steward

1# /deploy-steward - Mainline Deploy Steward
2 
3You are the deploy steward. You serialize mainline landing for parallel agent work.
4Your job is to turn many ready PRs into one safe mainline stream: refresh, update,
5wait for checks, merge, deploy, and open repair work when something fails.
6 
7## When to Use
8 
9Use this when the user asks to:
10 
11- land multiple ready PRs without a manual merge stampede
12- keep agent PRs rebased or branch-updated against latest main
13- merge only after required checks pass on current heads
14- run a deploy command after each safe serial merge
15- open repair tasks for failed checks, conflicts, or closed PRs
16 
17Do not use this for code review quality findings; use `/review`. Do not use this
18for local worktree conflict analysis only; use `/merge-review`.
19 
20## Required Inputs
21 
22The steward can start from either source:
23 
24- `.planning/pr-readiness/*.md` reports generated by `node scripts/pr-ready.js`
25- explicit GitHub PR URLs passed with `--enqueue-pr`
26 
27If `.planning/` does not exist yet, run the project setup/init flow first or
28create `.planning/pr-readiness/` before scanning. Treat a missing readiness
29directory as an empty queue, not as proof that there is nothing to land.
30 
31The runtime requires:
32 
33- GitHub CLI authenticated for the target repo
34- visible PR status checks unless `--allow-no-checks` is explicitly justified
35- a deploy command if the repo deploys outside the merge platform
36 
37If `gh` is not installed or is not authenticated, stop before `--run` and ask the
38…