@reach_vb: Codex tip: use codex exec to turn any prompt into a repeatable, scriptable workflow. I typically use it for clean, isol…
Summary
A tip on using codex exec to create repeatable, scriptable workflows for clean, isolated model runs, useful for evals, batch jobs, CI, and comparing prompts or models.
View Cached Full Text
Cached at: 07/31/26, 12:43 AM
Codex tip: use codex exec to turn any prompt into a repeatable, scriptable workflow.
I typically use it for clean, isolated model runs: ephemeral sessions, a pinned model and reasoning effort, no network or MCP access, and a separate directory for every run.
It’s super useful for evals, batch jobs, CI, scheduled workflows, and comparing prompts or models without local state affecting the results.
Similar Articles
@reach_vb: Codex Tip: ask Codex to look through your past sessions and turn repeated prompts into reusable skills + subagents you’…
A tip for using Codex to turn repeated prompts into reusable skills and subagents, improving workflow efficiency for tasks like CI failure checking and PR review.
@OpenAIDevs: Show Codex a workflow once. Reuse it as a skill. Record & Replay lets you show Codex a recurring task, like filing an e…
OpenAI introduces Record & Replay for Codex, allowing users to demonstrate a workflow once and turn it into a reusable, inspectable skill.
@rileybrown: You can now prompt Codex to spin up new threads inside Codex.
Codex now allows users to prompt it to create new threads within its interface.
@steipete: If you run this workflow, ask Fable to make codex the workhorse. https://github.com/steipete/agent-scripts/blob/main/sk…
A GitHub repository by steipete providing shared agent instructions, reusable workflow skills, and helper scripts for configuring Codex and Claude-style AI agents in local development environments.
@PaulSolt: https://x.com/PaulSolt/status/2073470146115490230
Paul Solt shares a detailed workflow for using Codex agents in a loop to autonomously build features overnight, including a manager thread, heartbeat, and automated PR review. The technique shifts from single prompts to designed agent loops, enabling continuous development with minimal human intervention.