# Codex First

Claude Code / OpenClaw-on-Claude work routing: delegate hands-on work to Codex under...

- Repository: https://github.com/steipete/agent-scripts (7431 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-10-30
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add steipete/agent-scripts --skill codex-first -g -a claude-code -y`
Codex: `npx skills add steipete/agent-scripts --skill codex-first -g -a codex -y`
Cursor: `npx skills add steipete/agent-scripts --skill codex-first -g -a cursor -y`
Gemini CLI: `npx skills add steipete/agent-scripts --skill codex-first -g -a gemini-cli -y`

## Description

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.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# 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** (`service_tier="fast"`, sent as API `priority`;
Peter, 2026-10-30). Pass all three settings unless the user requests an override.

```bash
# fresh
codex exec --yolo -C "$WT" \
  -m gpt-6.1-sol -c 'model_reasoning_effort="high"' \
  --enable fast_mode -c 'service_tier="fast"' \
  -o "$OUT" - < "$ORDER"
# resume: pass the same flags again; resume does not inherit them
codex exec resume "$SID" --dangerously-bypass-approvals-and-sandbox \
  -m gpt-6.1-sol -c 'model_reasoning_effort="high"' \
  --enable fast_mode -c 'service_tier="fast"' -o "$OUT" -
```

- 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 'service_tier="ultrafast"'` and add
  `-c 'model_auto_compact_token_limit=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.service_tier`). Details: [launch details](references/launch-details.md).
- 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)

The rest: https://github.com/steipete/agent-scripts/blob/HEAD/skills/codex-first/SKILL.md