Meta Packager

Use this workflow when the user asks Codex to turn repeated recent work into reusable assets, such as skills, custom subagents, or automations.

Workflow

1. Collect evidence in this order: recent Codex sessions and task summaries, Codex memories under ~/.codex/memories/, Chronicle-derived memories under ~/.codex/memories_extensions/chronicle/ when present, then existing skills, subagents, hooks, and automations.
2. Inventory existing reusable assets before proposing anything new. Check repository-local assets first, then user-level assets such as ~/.codex/skills, ~/.agents/skills, ~/.codex/automations, and any project codex/, .codex/, or .agents/ directories.
3. Group candidate patterns by repeated user intent, not by exact prompt wording. Count only eligible occurrences from the collected evidence.
4. For each candidate, record occurrence count, stable inputs, expected outputs, tools or commands used, failure modes, and overlapping existing assets.
5. Apply all creation gates before packaging: at least two occurrences, stable inputs and outputs, material time or error-reduction benefit, no existing asset already covers most of the workflow, and no repository policy conflict.
6. Choose the smallest package type that fits: skill for repeatable procedural work, custom subagent for read-heavy parallel triage with a summary returned to the parent, automation for hook-driven or scheduled behavior with deterministic triggers.
7. Output a shortlist table before editing files. Mark low-confidence, one-off, or duplicate candidates as deferred instead of creating them.
8. Create only high-confidence items. Prefer extending an existing asset over creating a parallel skill, subagent, or automation.
9. For custom subagents, include an explicit reminder that they require deliberate parallel invocation and do not run automatically.
10. Update README or docs/ when adding or changing reusable harness concepts, then run relevant verification.

Evidence Hints