jeremylongshore Flush
Manually flush the deferred-commit queue from a chain that ran with commit-when=end. Normally /hyperflow:dispatch calls scripts/flush-commits.sh at its Step 4 wrap-up; this skill exists for the case where the chain was interrupted (crash, kill, context loss) before the auto-flush ran.
Subcommands
| Subcommand | Description |
|---|---|
| (no arg) | Run scripts/flush-commits.sh <project-root> — fast-forward staging onto user's branch, delete staging, clear queue |
--dry-run |
Show what would be flushed without doing it. Lists the queued commits in order. |
What gets flushed
.hyperflow/commits-queue/manifest.json tracks the chain's user_branch, staging_branch (always hyperflow/staging-<chain-id>), and the list of queued commits with SHAs and messages. Flush replays them via git merge --ff-only so:
- All N commits land on the user's branch with original SHAs preserved
- Order is chronological (queue-time order)
- Original commit messages are preserved
- Original file-to-message mapping is preserved (each commit touched exactly the files its sub-task touched)
What happens if fast-forward isn't possible
If the user's branch diverged from staging (e.g. the user committed manually mid-chain on the same branch), git merge --ff-only refuses. The skill surfaces the error with two recovery options:
git rebase hyperflow/staging-<chain-id>— replay staging commits on top of user's new commitsgit cherry-pick <staging-base>..hyperflow/staging-<chain-id>— selectively pick commits
The staging branch is preserved for the user to act on manually. The queue manifest stays in place so a future /hyperflow:flush retry can attempt again after the user resolves divergence.
Flow
- Check
.hyperflow/commits-queue/manifest.jsonexists. If not, printNo queue to flush.and stop. - Run
bash $PLUGIN_ROOT/scripts/flush-commits.sh $PROJECT_ROOT [--dry-run]. - Print the script's output verbatim.
Overview
/hyperflow:flush is the user-facing handle for the deferred-commit flush mechanism. Most users never call it explicitly — /hyperflow:dispatch Step 4 wrap-up runs the same script automatically. This skill exists for recovery: if a chain ran with commit-when=end and crashed before wrap-up, the queue persists on disk and the user can flush it later.
Prerequisites
.hyperflow/commits-queue/manifest.jsonexists from a prior chain run withcommit-when=end.- Git repository, on a branch the manifest's
user_branchfield can be checked out into. scripts/flush-commits.shavailable in the plugin install.
Error Handling
| Failure | Behavior |
|---|---|
| No manifest file present | Print No queue to flush. Exit 0. |
| Staging branch missing (manual deletion or rename) | Print warning; clear stale manifest. Exit 0. |
| Fast-forward not possible (user branch diverged) | Surface git error + recovery suggestions (rebase / cherry-pick). Leave staging branch + manifest intact for manual handling. Exit non-zero. |
| User on a branch other than manifest's user_branch | Check out manifest's user_branch automatically; if checkout fails, surface error. |
Examples
Dry-run before flushing
/hyperflow:flush --dry-run
flush-commits (DRY RUN): would fast-forward 7 commits from hyperflow/staging-2026-05-17-1430 onto feat/auth-refactor
abc1234 feat(auth): T7 wire login handler
def5678 feat(auth): T6 add session middleware
…
Recovery after crash
You: /hyperflow:flush
flush-commits: flushed 7 commits onto feat/auth-refactor
abc1234 feat(auth): T7 wire login handler
…
Resources
scripts/flush-commits.sh— the actual flush mechanism.scripts/queue-commit.sh— the queue-write side called by dispatch during the chain.- DOCTRINE.md Layer 8 —
commit-whentiming rules.
Source: jeremylongshore/claude-code-plugins-plus-skills → plugins/ai-agency/hyperflow/skills/flush/SKILL.md