codex-cli-runtime

An internal helper for a Claude Code rescue worker to send one request to the Codex companion runtime and return its response unchanged.

In plain words
What is it for?
Use it when a rescue workflow needs to forward a repository-related request to Codex.
Why use it?
It gives the rescue worker one defined way to pass diagnosis, planning, research, or fix requests to Codex without doing the work 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/vsladkov/claudex-stereo/codex-cli-runtime
Any agent
npx skills add vsladkov/claudex-stereo --skill codex-cli-runtime
Clone the repo
git clone --depth 1 https://github.com/vsladkov/claudex-stereo

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 866 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00866
Opus 5 $0.00010 $0.00433
Sonnet 5 $0.00004 $0.00173
Haiku 4.5 $0.00002 $0.00087

Measured 2d ago against content hash b74209fa4a85, 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 2d ago.

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.

plugins/stereo/skills/codex-cli-runtime/SKILL.md · 49 lines

What it actually says

Codex Runtime

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

Primary helper:

  • node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.ts" 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 stereo:codex-rescue.
  • Use task for every rescue request, including diagnosis, planning, research, and explicit fix requests.
  • You may use the codex-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. Task runs never inject an effort default; the pair workflow applies defaults only to OpenAI gpt-* models. An explicit --effort is forwarded verbatim, including for provider models that may ignore or reject it. Never invent an effort the user did not ask for.
  • Leave model unset by default. Add --model only when the user explicitly asks for one, then pass that value through verbatim — a model id or one of the plugin aliases (codex:mini, codex:sol, codex:terra, codex:luna, codex:kimi, codex:qwen, codex:deepseek, codex:glm); the runtime resolves aliases itself, and /stereo:setup shows each provider alias's readiness. The bare form without the codex: prefix is also accepted; forward either verbatim because the runtime strips the prefix.
  • 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.
  • The Agent invocation and Bash call are always foreground. Strip --wait and make a foreground task call; map --background to task --background. Neither flag is part of the natural-language task text.
  • If the forwarded request includes --model, pass it through to task without expanding aliases.
  • If the forwarded request includes --effort, pass it through to task.
  • Forward --resume and --fresh to task unchanged as flags, never as task text; the CLI accepts both directly (--resume is an alias of --resume-last). --resume always resumes, and --fresh always runs fresh, even when the request text is ambiguous.
  • --effort: accepted values are none, minimal, low, medium, high, xhigh, max.
  • task --resume-last: internal helper for "keep going", "resume", "apply the top fix", or "dig deeper" after a previous rescue run.

Safety rules:

  • 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 exactly Codex rescue failed: <first line of the error>. Run /stereo:setup to check the Codex CLI. and add nothing else.
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. 2d ago First seen · 49 lines · 19 tokens per session scan A b74209fa4a85

Subscribe to this mod's changes

codex-cli-runtime is a skill published in the GitHub repository vsladkov/claudex-stereo (3 stars, last pushed 23d ago), licensed Apache-2.0. It adds 19 tokens to every session and 866 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.