Show HN: Codex Self-Reflect Skill and CLI to run subagents on past Codex convos
github.comThis skill is useful for identifying agent friction points and brainstorming new skills, developing context of past work for a new conversation, identifying code bloat from failed solutions, etc.
It is a simple Codex meta-"skill" that uses a CLI to analyze your past Codex sessions and generate reflections. It uses headless Codex subagents running in parallel on temporary copies of conversation history. These reflections are orchestrated by the CLI and a Codex agent can synthesize them for downstream use. Reflections are cached for efficiency.
Repo: https://github.com/olliepro/Codex-Reflect-Skill Seems like this would be useful to run on some sort of cadence to get daily reflections from AI agents. I'm gonna connect this up to my email MCP so that I get a daily notification with Codex's reflections. I was thinking about something like this, but I don't have codex running on a server. Keep me posted on how it goes!