Claude Code

One command connects Claude Code on your computer to an OpenCode Console workspace. You keep running claude as before, with these changes:

• /model lists the workspace's models, including ones from other providers. Requests go through Console, so the workspace's model rules and budgets apply. opus, sonnet and haiku point to the newest Claude models the workspace offers.
• Every tool call, and every file or skill a prompt mentions, is checked against the workspace's policies first. A blocked call stays blocked even with --dangerously-skip-permissions.
• The workspace's MCP servers are added, with OpenCode Web Search when the workspace offers it.
• The workspace's Library skills are added to ~/.claude/skills, so you can run each one as /name. Its Library instructions are added to ~/.claude/CLAUDE.md.

Claude Code picks up changes in Console when a session starts, and on tool calls once its copy is more than a minute old. OpenCode doesn't need this command, since it connects to Console itself.

• An OpenCode Console workspace you're a member of.
• Claude Code 2.1.295 or later.
• Node.js 22 or later, for npx.

1. Run this in a terminal:
   npx @opencode/console setup claude-code
2. Your browser opens Console. Check that the code matches the one in your terminal, approve the sign-in and pick the workspace.
3. Setup prints the models, policies, MCP servers and Library items it set up. Run claude to start.

Run the command again any time to update the setup. If the workspace offers no models, Claude Code keeps its own sign-in and still gets the workspace's policies, MCP servers and Library. If ANTHROPIC_API_KEY or ANTHROPIC_AUTH_TOKEN is set in your shell, Claude Code uses it instead of the workspace, so unset it first.

To see who you're signed in as, the workspace, and how many policies and models it has, run:

To undo setup, run:

It puts back the settings setup changed, unless you've changed them since, and removes its hooks, MCP servers, skills and instructions. You stay signed in until you run npx @opencode/console logout.

• Policies are checked by hooks in your Claude Code settings, so they hold only while those settings are in place. Console enforces model rules, budgets and MCP tool rules itself, on every request that goes through it.
• Until Claude Code has the workspace's policies, it blocks every tool call. If Console can't be reached, the policies it last fetched stay in place.
• Running setup again overwrites settings you've changed by hand. If you already have an MCP server or skill with the same name as one of the workspace's, setup keeps yours.

Email help@anoma.ly. We reply within two business days (Monday to Friday, excluding US holidays). The support page covers data requests, security reports and more.