OpenAI Codex team's Nick Baumann: build dedicated CLI tools for AI instead of feeding messy data repeatedly

OpenAI Codex 团队的 Nick Baumann 分享了一个他日常用 Codex 干活的心得：与其每次把一堆文档、日志、API 输出丢给 AI 去啃，不如给它造几个专用的命令行小工具。

OpenAI Codex engineer Nick Baumann says teams should wrap repeated data access into parameterized CLI tools with JSON output instead of repeatedly dumping logs, docs, and API responses into Codex. The post lists 3 examples in daily use: codex-threads for past sessions, slack-cli for threaded Slack search, and typefully-cli for posting workflows; access still goes through the existing auth gateway. The point for practitioners is narrower interfaces: models handle focused commands more reliably than raw, noisy source data.

Why it matters: This is a practical workflow note from an OpenAI Codex team member, not a formal launch, but it offers a reusable mechanism: wrap noisy context behind parameterized JSON-returning CLIs and shows 3 live examples. HKR-H/K/R all land; no benchmark, scale, or major product release,so