codex-cli-runtime

An internal helper for sending one request from Claude Code to the Codex command-line tool. It is intended for a specific rescue subagent.

In plain words
What is it for?
It helps forward coding, diagnosis, planning, research, or fix requests to Codex and return Codex's output unchanged.
Why use it?
It keeps that subagent focused on forwarding the request instead of inspecting the project or trying to solve the task itself.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/greenpolo/cc-multi-cli-plugin/codex-cli-runtime
Any agent
npx skills add greenpolo/cc-multi-cli-plugin --skill codex-cli-runtime
Clone the repo
git clone --depth 1 https://github.com/greenpolo/cc-multi-cli-plugin

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 768 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00768
Opus 5 $0.00010 $0.00384
Sonnet 5 $0.00004 $0.00154
Haiku 4.5 $0.00002 $0.00077

Measured yesterday against content hash 5ba31a12ef45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-cli-runtime scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

86% identical to codex-cli-runtime — 15 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/multi/skills/codex-cli-runtime/SKILL.md · 43 lines

What it actually says

Codex Runtime

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

Primary helper:

  • node "${CLAUDE_PLUGIN_ROOT}/scripts/multi-cli-companion.mjs" task --cli codex "<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 multi: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.
  • 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.
  • Run task in the FOREGROUND (no --background) so the call returns Codex's real result; the parent command handles background scheduling by running this subagent as a harness background task (that is what notifies the main thread). --background / --wait are Claude-side scheduling controls — strip them from the natural-language task text; only honor an explicit --background as user-requested fire-and-forget polled via /multi:status.
  • If the forwarded request includes --model, pass the slug through to task verbatim.
  • 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 multi: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.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 43 lines · 19 tokens per session scan A 5ba31a12ef45

Subscribe to this mod's changes

codex-cli-runtime is a skill published in the GitHub repository greenpolo/cc-multi-cli-plugin (89 stars, last pushed 16d ago), licensed Apache-2.0. It adds 19 tokens to every session and 768 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to codex-cli-runtime, differing in 15 lines, and is treated as a copy.

Related

Other skills, from other repositories

copilot-pr-review-loop

Drive a GitHub pull request through repeated rounds of Copilot code review until convergence. Use when the user asks to "request Copilot review", "run a Copilot review loop", iterate on Copilot feedback, or wants automated triage-and-respond on Copilot PR comments. Covers re-request mechanics, open-thread filtering…

microsoft/intelligent-terminal · 91 tokens

upstream-sync

Periodically sync new commits from microsoft/terminal into this manually-forked intelligent-terminal repo by cherry-picking commit-by-commit onto a dated sync branch, auto-skipping revert pairs and empty commits, auto-resolving known take-upstream files, and stopping cleanly on genuine conflicts. The agent (you…

microsoft/intelligent-terminal · 139 tokens

release-notes

Generate user-facing release notes for Intelligent Terminal. Use when asked to write release notes, changelog, what-is-new summary, or prepare a release. Compares git commits between releases, looks up PR-linked issues and community contributors, then outputs formatted notes with "Verbed + Impact + Scenario" style…

microsoft/intelligent-terminal · 73 tokens

add-acp-agent-support

Add first-class support for an ACP-compatible agent CLI to Intelligent Terminal. Use when integrating a new built-in AI agent, ACP server command, authentication flow, model selection, interactive delegation, session hooks, onboarding, Settings, branding, GPO policy, documentation, tests, build, deployment, or live…

microsoft/intelligent-terminal · 72 tokens

pr-integration-test

Design, implement, and validate Intelligent Terminal integration tests for a target pull request or regression. Use when asked to add PR integration tests, convert a bug fix into E2E coverage, prove existing behavior still works, map tests to the release checklist, or verify E2E reports mark checklist cases complete.

microsoft/intelligent-terminal · 66 tokens

opentag

Use when installing, pairing, operating, or troubleshooting OpenTag through the published CLI, self-hosted Control Plane, governed completion, supported collaboration platforms, or built-in coding agents.

amplifthq/opentag · 40 tokens