Codex Cli Runtime

openai/codex-plugin-cc/plugins/codex/skills/codex-cli-runtime

by openaidb52e28f4d9ded852ab3942cea316258ae4ef346No licenseListed Oct 9, 2026Updated Oct 9, 2026

Internal helper contract for calling the codex-companion runtime from Claude Code

FeaturedInstructions onlyAI & Agents
AI-generated overview

Internal helper contract for forwarding a single task to the codex-companion runtime from a rescue subagent.

What it does
This skill defines an internal helper contract used inside a specific rescue subagent. It instructs the agent to invoke one codex-companion task command with the user's raw arguments and return that command's stdout unchanged. It also specifies flag handling, such as stripping routing flags, mapping a shorthand model name, and defaulting to a write-capable run. It is not user-invocable and produces no artifacts of its own beyond the forwarded command output.
When to use it
Use it only within the codex:codex-rescue subagent when a request must be handed off to the codex-companion runtime. It is meant for diagnosis, planning, research, and explicit fix requests that should be forwarded rather than solved locally.
Requirements
Requires the codex-companion runtime invoked through Node.js at a plugin-relative script path, plus the Codex CLI it wraps. It ships no scripts of its own and is instructions only; it references another prompting skill for optional prompt rewriting.

Codex Runtime

Use this skill only inside the codex:codex-rescue subagent.

Primary helper:

  • node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" task "<raw arguments>"

Execution rules:

  • The rescue subagent is a forwarder, not an orchestrator. Its only job is to invoke task once and return that stdout unchanged.
  • Prefer the helper over hand-rolled git, direct Codex CLI strings, or any other Bash activity.
  • Do not call setup, review, adversarial-review, status, result, or cancel from codex:codex-rescue.
  • Use task for every rescue request, including diagnosis, planning, research, and explicit fix requests.
  • You may use the gpt-5-4-prompting skill to rewrite the user's request into a tighter Codex prompt before the single task call.
  • That prompt drafting is the only Claude-side work allowed. Do not inspect the repo, solve the task yourself, or add independent analysis outside the forwarded prompt text.
  • Leave --effort unset unless the user explicitly requests a specific effort.
  • Leave model unset by default. Add --model only when the user explicitly asks for one.
  • Map spark to --model gpt-5.3-codex-spark.
  • Default to a write-capable Codex run by adding --write unless the user explicitly asks for read-only behavior or only wants review, diagnosis, or research without edits.

Command selection:

  • Use exactly one task invocation per rescue handoff.
  • If the forwarded request includes --background or --wait, treat that as Claude-side execution control only. Strip it before calling task, and do not treat it as part of the natural-language task text.
  • If the forwarded request includes --model, normalize spark to gpt-5.3-codex-spark and pass it through to task.
  • If the forwarded request includes --effort, pass it through to task.
  • If the forwarded request includes --resume, strip that token from the task text and add --resume-last.
  • If the forwarded request includes --fresh, strip that token from the task text and do not add --resume-last.
  • --resume: always use task --resume-last, even if the request text is ambiguous.
  • --fresh: always use a fresh task run, even if the request sounds like a follow-up.
  • --effort: accepted values are none, minimal, low, medium, high, xhigh.
  • task --resume-last: internal helper for "keep going", "resume", "apply the top fix", or "dig deeper" after a previous rescue run.

Safety rules:

  • Default to write-capable Codex work in codex:codex-rescue unless the user explicitly asks for read-only behavior.
  • Preserve the user's task text as-is apart from stripping routing flags.
  • Do not inspect the repository, read files, grep, monitor progress, poll status, fetch results, cancel jobs, summarize output, or do any follow-up work of your own.
  • Return the stdout of the task command exactly as-is.
  • If the Bash call fails or Codex cannot be invoked, return nothing.

Source and attribution

Source:openai/codex-plugin-ccinplugins/codex/skills/codex-cli-runtimeat commitdb52e28

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal