Read open GitHub issues on one repo (paginated - big repos are never silently truncated), skip the ones already queued, launch a detached Codex run per new issue (write-tier, approval-gated), and queue each as an open codex_queue row for the sweeper. Attach a schedule to this recipe's dish per repo: 10 repos = 10 dishes of this one template. Stage 1 of the Codex workflow - sweep-codex-results reconciles outcomes and the handler dishes react to them.

How it works 15 steps

Inspect the data fetches, transforms, gates, and output this recipe runs.

Process (15 steps)

■ issues_raw ?

■ issues default

Apply default

⚠ guard_issues guard

Stop if issues is empty

■ repo_slash replace

Replace text in setting repo

■ repo_key replace

Replace text in repo slash

■ real_issues filter

Filter by condition

■ existing ?

■ existing_keys map

Extract from each item

■ keyed_issues map

Extract from each item

■ new_issues filter

Filter by condition

■ now date_add

Add 0 days to

■ launch ?

■ queue_rows ?

■ new_count count

Count items in new issues

■ card to_summary

Format results as a summary card

Settings 4 configurable

Configurable at install. Defaults shown — change them anytime in Recued.

repo setting = —

github setting =

repo dir setting = —

result dir setting = —