Give your Grok Bot team Claude and ChatGPT models by installing their CLIs
A coach had his Chief of Staff Bot install the Claude Code and Codex command-line tools on its own computer, then routed writing to Claude Opus 5.5 and coding to another model.
Explain it simply
A coach had his AI assistant install two other companies' AI tools on its own computer. Now his assistants send writing jobs to one model and coding jobs to another. Check each company's rules before you copy this.
What was done
Corey Ganim sent his Chief of Staff Bot a link to Andrew Warner's post describing the method.
The Bot opened a terminal on its cloud computer and installed the ChatGPT and Claude command-line tools; Corey signed in to each one once.
He then updated every Bot's instructions, plus Grok Bot's shared memory, to send writing to Claude Opus 5.5 and coding and computer-use tasks to a model he called "6.1 Sol."
How it went
He says it works extremely well, but gives no metrics or before-and-after comparison.
- Replies raise unverified concerns: whether this fits Anthropic's terms, and whether signing in from a data-center IP risks a ban.
- One user found their CLAUDE.md settings and memories didn't carry over to the Bot's computer.
- Others say Grok Bot already routes some tasks to models like Opus 5.5 natively, so this may matter less over time.
Prompt
Open a terminal on your computer and install the Claude Code and Codex command-line tools. Tell me when each one needs me to sign in, and wait.
After I'm signed in, update every Bot's instructions and our shared memory with this rule: use Claude Opus for writing tasks and [your chosen coding model] for coding and computer-use tasks.
Show me the exact text you changed.
Setup notes
- Sign in with your own subscriptions.
- Read each provider's current terms on automated or remote use before relying on this.
- Re-create any CLAUDE.md or settings you depend on; they won't be on the Bot's computer.
Business fit
Who this helps, and how:
- Solo foundersOwners who prefer one model's writing can get it inside their Bot team.
- AgenciesAgencies can standardize which model writes client copy across Bots.
- StartupsTechnical founders can mix models per task without leaving Grok Bot.
Related
Similar tools
Other tools for this job, and how they differ. Chosen by our editors, never paid for.
- Hermes Agent
Open source and model-agnostic, so it isn't tied to one AI company's models; you host it yourself.
- OpenClaw
Self-hosted framework where you choose the model; Felix, the agent in another use case here, runs on Claude Opus 4.6.
See it in use: Give an always-on agent a revenue target and let it run the business
Evidence grade D means: A brief, early or in-progress claim. Treat it as an idea to test, not proof. How we grade. Spotted a mistake? Suggest a correction.