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.
npx agentmods add skills/jinxlzc/grok-codex-plugin/codex-cli-runtimenpx skills add jinxlzc/grok-codex-plugin --skill codex-cli-runtimegit clone --depth 1 https://github.com/jinxlzc/grok-codex-pluginWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00020 | $0.00759 |
| Opus 5 | $0.00010 | $0.00380 |
| Sonnet 5 | $0.00004 | $0.00152 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
codex-cli-runtime scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
95% identical to codex-cli-runtime — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Codex Runtime
Use this skill only inside the codex:codex-rescue subagent.
Primary helper:
node "${GROK_PLUGIN_ROOT:-$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
taskonce 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, orcancelfromcodex:codex-rescue. - Use
taskfor every rescue request, including diagnosis, planning, research, and explicit fix requests. - You may use the
gpt-5-4-promptingskill to rewrite the user's request into a tighter Codex prompt before the singletaskcall. - That prompt drafting is the only Grok-side work allowed. Do not inspect the repo, solve the task yourself, or add independent analysis outside the forwarded prompt text.
- Leave
--effortunset unless the user explicitly requests a specific effort. - Leave model unset by default. Add
--modelonly when the user explicitly asks for one. - Map
sparkto--model gpt-5.3-codex-spark. - Default to a write-capable Codex run by adding
--writeunless the user explicitly asks for read-only behavior or only wants review, diagnosis, or research without edits.
Command selection:
- Use exactly one
taskinvocation per rescue handoff. - If the forwarded request includes
--backgroundor--wait, treat that as Grok-side execution control only. Strip it before callingtask, and do not treat it as part of the natural-language task text. - If the forwarded request includes
--model, normalizesparktogpt-5.3-codex-sparkand pass it through totask. - If the forwarded request includes
--effort, pass it through totask. - 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 usetask --resume-last, even if the request text is ambiguous.--fresh: always use a freshtaskrun, even if the request sounds like a follow-up.--effort: accepted values arenone,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-rescueunless 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
taskcommand exactly as-is. - If the Bash call fails or Codex cannot be invoked, return nothing.
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.
- 2d ago First seen · 44 lines · 20 tokens per session scan A c8e14350f8b3
codex-cli-runtime is a skill published in the GitHub repository jinxlzc/grok-codex-plugin (1 stars, last pushed 19d ago), licensed Apache-2.0. It adds 20 tokens to every session and 759 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to codex-cli-runtime, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
grok-cli-runtime
Internal helper contract for calling the grok-companion runtime from Codex.
grok-workflows
When and how to run Grok Rhai multi-agent workflows from Codex.
grok-routing
When Codex should delegate to Grok vs handle work itself.
grok-workflows
When and how to run Grok Rhai multi-agent workflows from Codex.
goal-verifier
Independently verify a Grok Build goal is truly complete. Checks GOAL.md done conditions, runs tests, and returns PASS or REJECT with evidence. Use before updategoal(completed: true), when asked to "verify goal", "check if done", or as a reviewer sub-agent at the end of a goal run.
grok-routing
When Codex should delegate to Grok vs handle work itself.