Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
openai avatar

Codex Cli Runtime

  • 609 installs
  • 31.2k repo stars
  • Updated July 8, 2026
  • openai/codex-plugin-cc

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

About

Internal helper contract for calling the codex-companion runtime from Claude Code. Use this skill only inside the `codex:codex-rescue` subagent. The codex-cli-runtime skill documents workflows, constraints, and examples from SKILL.md for agent-assisted execution.

  • Use this skill only inside the `codex:codex-rescue` subagent.
  • `node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" task "<raw arguments>"`
  • The rescue subagent is a forwarder, not an orchestrator. Its only job is to invoke `task` once and return that stdout un
  • 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`.

Codex Cli Runtime by the numbers

  • 609 all-time installs (skills.sh)
  • +21 installs in the week ending Jul 26, 2026 (Skillselion tracking)
  • Ranked #1,562 of 16,556 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
At a glance

codex-cli-runtime capabilities & compatibility

Capabilities
use this skill only inside the `codex:codex resc · `node "${claude_plugin_root}/scripts/codex compa · the rescue subagent is a forwarder, not an orche · prefer the helper over hand rolled `git`, direct
Use cases
documentation
From the docs

What codex-cli-runtime says it does

Internal helper contract for calling the codex-companion runtime from Claude Code
SKILL.md
npx skills add https://github.com/openai/codex-plugin-cc --skill codex-cli-runtime

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs609
repo stars31.2k
Last updatedJuly 8, 2026
Repositoryopenai/codex-plugin-cc

How do I apply codex-cli-runtime using the workflow in its SKILL.md?

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

Who is it for?

Developers following the codex-cli-runtime skill for the tasks it documents.

Skip if: Tasks outside the codex-cli-runtime scope described in SKILL.md.

When should I use this skill?

User mentions codex-cli-runtime or related triggers from the skill description.

What you get

Working codex-cli-runtime setup aligned with the documented patterns and constraints.

  • forwarded Codex task output
  • rescue subagent stdout

Files

SKILL.mdMarkdownGitHub ↗

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.

Related skills

FAQ

What does codex-cli-runtime do?

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

When should I use codex-cli-runtime?

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

Is codex-cli-runtime safe to install?

Review the Security Audits panel on this page before installing in production.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.