openai-codex-operator
v1.0.1Run OpenAI Codex CLI from OpenClaw for coding tasks in a target project directory. Use when the user asks OpenClaw to use Codex for implementation, debugging, refactoring, review, or scripted coding workflows.
Installation
Please help me install the skill `openai-codex-operator` from SkillHub official store.
npx skills add cecwxf/openai-codex-operator
OpenAI Codex Operator
Use this skill to reliably call Codex CLI from OpenClaw.
Core rules
- Verify Codex CLI exists (
codex --version) before first task. - Always run Codex through OpenClaw
execwithpty:true. - Always set explicit
workdirto the target repository. - For long tasks, use
background:trueand track viaprocess. - Report clear milestones: started, waiting-input, finished/failed.
Execution patterns
One-shot coding task
Use:
- exec.command: codex exec "<task>"
- exec.pty: true
- exec.workdir: <repo path>
Interactive session
Use:
- exec.command: codex
- exec.pty: true
- exec.workdir: <repo path>
Long-running background task
- Start with
exec(background:true, pty:true, workdir, command:"codex exec ...") - Record returned
sessionId. - Poll with
process action:poll. - Read output with
process action:log. - If Codex asks for input, use
process action:submit.
Recommended prompts
- "Implement
with tests, run tests, and summarize changed files." - "Find root cause for failing CI in this repo and propose minimal fix."
- "Review current branch diff and list high-risk issues first."
Guardrails
- Do not claim files were changed unless logs show completion.
- If
codexis missing or auth fails, return exact remediation steps. - Keep OpenClaw tool config (
pty/workdir/background) separate from CLI args.
References
references/codex-doc-summary.mdreferences/codex-usage-recipes.mdscripts/run-codex-example.sh