Quick start: connect Claude Code and Codex

One command signs you in and connects Claude Code and Codex. You keep your agent, your model and your provider account.

npx @context-mode/cli

It does five things:

1. Signs you in, in the browser, if this terminal is not signed in yet.
2. Finds Claude Code and Codex on this machine.
3. Asks which of them to connect.
4. Writes each one's config and keeps a backup of the old file.
5. Sends one test request per agent, prints one line for each, then prints the console address.

Start free: 2,000 requests, every feature, no card. When the free requests run out, nothing breaks: see Plans and limits. Your own Claude or OpenAI account still pays the model.

Restart Claude Code, or start a new Codex session. Then open the console to watch each request's tokens, cost and saving.

What it writes

Claude Code, in ~/.claude/settings.json under env:

"ANTHROPIC_BASE_URL": "https://gateway.context-mode.com",
"ANTHROPIC_CUSTOM_HEADERS": "x-cm-device-key: cmdk_…",
"ENABLE_TOOL_SEARCH": "true"

Claude Code turns tool search off for any base URL that is not Anthropic's and then sends every tool in full. ENABLE_TOOL_SEARCH turns it back on.

Codex, in ~/.codex/config.toml:

model_provider = "context-mode"

[model_providers.context-mode]
name = "context-mode"
base_url = "https://gateway.context-mode.com"
wire_api = "responses"
requires_openai_auth = true
http_headers = { "x-cm-device-key" = "cmdk_…" }

Codex sends a credential only from its own login. A ChatGPT login and an API key both work. An OPENAI_API_KEY that is only exported in your shell is not sent, so the CLI tells you to run codex login --with-api-key.

Codex

Codex gets the same gateway as Claude Code: Context Saving, Cage, Memory, Skills, Search, Session resume and the context limit. Both clients share one store per account, so a fact you state in one is there in the other, and codex resume can open a session that started in Claude Code.

Cage and the Codex sandbox. OpenAI's Codex docs say sandboxing and approvals are different controls that work together: the sandbox defines technical boundaries, and the approval policy decides when the agent must stop and ask before crossing them (Codex sandboxing, read 2026-10-01). Cage is a third check, on the gateway. It checks each call Codex makes, including exec_command, apply_patch and tool-server calls inside one exec call, before Codex runs it. Cage reads the call, not the program, so keep the sandbox on, for example in workspace-write. See Cage docs.

Not done yet for Codex.

• Codex cost is not measured, so we quote no Codex saving.
• Tool-schema trimming runs for Claude Code only, and part of the saving on Codex is not counted yet.
• Cage does not match Codex's read_mcp_resource and list_mcp_resources calls with Tool servers rules.

The device key

Sign-in gives this terminal a device key. It is stored in ~/.context-mode/credentials.json and never printed. If you switch Claude or OpenAI accounts, the key stays, so your data stays in one workspace. The gateway removes the header before a request goes to Anthropic or OpenAI.

What the CLI promises

• It shows the change and asks before it writes.
• It copies the old file to <file>.cm-setup-bak-<timestamp> first.
• It never replaces a different base URL or Codex provider unless you say so.
• Run it again with nothing to change, and it writes nothing.

Commands

Each command runs as npx @context-mode/cli <command>. It needs Node 20.12 or later.