Agent skill · software engineering · steipete
codex-first
Claude Code / OpenClaw-on-Claude work routing: delegate hands-on work to Codex under the native-Claude model gate. Keep specification, judgment, and verification in Claude; prefer isolated Codex-backed autoreview.
Why this skill is useful
Adds a detailed workflow for delegating tasks between Claude and Codex, including specific commands and model checks that enhance the AI's operational capabilities.
What it needs
About 9k tokens when loaded. Last updated 2026-08-06. 6,510 stars on the source repository.
What this skill does
Codex First Launch flags — read first, copy verbatim Default every Codex worker, fresh or resumed, to GPT-6.1 Sol, high reasoning, Fast service tier (servicetier="fast", sent as API priority; Peter, 2026-10-30). Pass all three settings unless the user requests an override. Old Codex CLIs silently omit tiers they do not know (codex-cli 0.147 on Team warned not advertised and sent no tier); keep the CLI current. Verified on Team with 0.166.0, 2026-10-30. Ultrafast only on request: swap in -c 'servicetier="ultrafast"' and add -c 'modelautocompacttokenlimit=260000'. It is served up to ~282k prompt tokens, flaky at 288–294k, and silently fast at ≥300k (measured 2026-10-13); the 260k cap keeps it there. Rollouts record only the requested tier; prove the served tier with a direct probe (response.servicetier). Details: launch details. Context: workers get the base 500k window. Add -p sol61-1m (or -p astra-1m) only when the order needs a whole-repo context; see $codex-huge-context. Copy all model/reasoning/tier flags into wrappers; override only on user request. Verify launch arguments (fast default; requested ultrafast is valid). Security audits and cyber-classifier refusals → Daybreak Red (Peter, 2026-10-15/18) Security audit lanes (threat models, injection/secret-exposure audits, permission inventories, security review of hardening diffs) launch on Daybreak Red from the start (Peter 2026-10-18: "use daylight red model for security audits"). Implementation workers stay on Sol. Worker stops with This content was flagged for possible cybersecurity risk → relaunch or resume the same order on Daybreak Red (Peter: "use daybreak red if you hit a blocker with regular models"). Don't rephrase to dodge the classifier or hop between regular models. Direct API only: the ChatGPT-account route returns 400 not supported when using Codex with a ChatGPT account. Add -c 'modelprovider="openaiapidirect"' (API key via the provider's auth command in ~/.codex/config.toml). …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills steipete/codex-first