Ask Codex, Grok, or local DeepSeek for independent analysis.

Use for debugging hypotheses, architecture evaluation, repository reasoning, or a second opinion. The external model cannot inspect files beyond the supplied context and cannot modify the workspace.

Request a read-only code review from one external model.

Use for correctness, regression, security, concurrency, data-loss, or missing-test review. Claude must verify each material finding.

Ask an external model to propose a minimal unified diff.

This tool does not apply changes. Claude must inspect, validate, apply, format, test, and review any proposed patch.

Ask two or three external models the same question in parallel.

Use when independent opinions materially improve confidence. Claude must compare the outputs, verify claims against the repository, and synthesize the final conclusion.

List model IDs exposed by CLIProxyAPI and show whether the configured Codex, Grok, and DeepSeek models are currently available.

Verify connectivity to CLIProxyAPI and availability of configured companion models. This performs no model inference.