agentleFS
patrick-fupatrick-fu/awesome-skills/codex-async-followup/SKILL.md

codex-async-followup

Skill69 starsChanged 11 days agoMITView on GitHub

Schedule follow-ups in Codex App for long asynchronous waits when no independent work remains and no existing Goal covers the wait; resume work when the scheduled wakeup arrives.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check the current thread's Goal (get_goal when available).

    line 13
  2. Very specific:

    After starting asynchronous work, continue any independent work.

    line 23
  3. Distinctive:

    If scheduling is unavailable or fails, report the failure and the remaining wait.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Codex Async Follow-up

Resume asynchronous work from the conversation's existing context.

Check the current thread's Goal (get_goal when available). If a Goal already covers this wait, follow its continuation and stopping rules, and retire this skill's automatic heartbeat for the same wait.

For other waits, choose the continuation path for the session's role:

  • Global and project controllers use codex-session-controller for follow-up mode selection, checks, and scheduling.
  • Workers and ordinary tasks use the loop below for their own internal waits.
  1. After starting asynchronous work, continue any independent work. When none remains and the expected wait is long, such as a lengthy build or extended research running in a subagent or background task, use automation_update to schedule a one-time heartbeat in the current task (destination: "thread"), then end the turn. Choose a delay from the expected duration, usually 5, 10, or 15 minutes. Set the prompt to continue.
  2. On wakeup, check the existing work and apply step 1 again: reassess independent work and the expected wait before deciding whether to continue or schedule another wakeup and end the turn. Stay quiet when nothing actionable changed.
  3. Reuse this follow-up's automation ID for later checks. Pause or delete this follow-up when its work is complete or canceled, or its wait ends.

If scheduling is unavailable or fails, report the failure and the remaining wait.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.