second-opinion

name	second-opinion
description	Second opinion: request consultant advice or set its mode.

Second Opinion

Use this skill to invoke $consultant or to change Gemini-line consultant mode.

Toggle keys

Manage these keys in .gemini/.agents-mode.yaml:

• Legacy .gemini/.agents-mode is compatibility input only. Resolve Gemini overlay state in this order: local .gemini/.agents-mode.yaml, local legacy .gemini/.agents-mode, global ~/.gemini/.agents-mode.yaml, then global legacy ~/.gemini/.agents-mode. Normalize whichever file supplied the effective config into the canonical .yaml path in the same scope, do not recreate any legacy file, and do not synthesize a local override on read alone.

• consultantMode

• delegationMode

• parallelMode

• mcpMode

• preferExternalWorker

• preferExternalReviewer

• externalProvider

• externalPriorityProfile

• reserveResolver

• externalPriorityProfiles

• externalOpinionCounts

• externalModelMode

• externalCodexProfile

Gemini-line rules:

• externalProvider: auto resolves through the active named priority profile, not a Gemini-line default provider
• externalPriorityProfile defaults to balanced
• reserveResolver binds symbolic reserve to claude-sonnet, claude-wrapper, wrapper:<command>, or disabled
• balanced is the ordinary shipped production profile and keeps auto routing on codex | claude
• explicit providers are codex, claude, gemini, and qwen
• externalProvider: gemini is allowed only as an explicit self-provider override for a manual example or compatibility run
• externalProvider: qwen is allowed only as an explicit native example or compatibility run
• externalModelMode is the shared cross-provider model policy: runtime-default leaves the resolved production provider on its runtime default model/profile, while pinned-top-pro starts on the strongest documented provider-native model/profile on the production provider paths
• externalCodexProfile: default inherits externalModelMode when Codex is selected or auto-resolved; gpt-5.6-sol-max requests model gpt-5.6-sol with model_reasoning_effort = "max" for higher-complexity/hard lanes; gpt-5.6-terra selects the balanced Codex model tier (a distinct model, model_reasoning_effort = "high", not an effort downgrade) and must be verified against the installed Codex runtime; gpt-5.6-sol-xhigh (shipped as default in the Codex/Claude packs) pins model gpt-5.6-sol with model_reasoning_effort = "xhigh" regardless of externalModelMode, symmetric to Claude's opus-xhigh
• reserve matters only when an advisory/review profile order reaches that symbolic supplemental candidate and is bound through reserveResolver
• Gemini is WEAK MODEL / NOT RECOMMENDED; shipped and repo-local production auto profiles must keep Gemini and Qwen out of provider-order lists

Toggle actions

• enable -> consultantMode: external
• internal -> consultantMode: internal
• disable -> consultantMode: disabled
• status -> read and normalize .gemini/.agents-mode.yaml, then print the current resolved values
• If local .gemini/.agents-mode.yaml is missing, read local legacy .gemini/.agents-mode as compatibility input only; if both local files are missing, fall back through pack-local global ~/.gemini/.agents-mode.yaml, pack-local global legacy ~/.gemini/.agents-mode, then the shared cross-pack global ~/.agents-mode.yaml (alongside ~/.claude.json), before applying built-in defaults (each key resolves to the highest layer that defines it; layers compose, they do not replace each other wholesale) and reporting status

Preserve unknown keys on write and normalize comment-free, partial, or older-layout files to the current canonical format on read. Keep one key per line with inline allowed-value comments. Legacy .gemini/.agents-mode is compatibility input only and must not be recreated.

Advisory run

When not in toggle mode:

1. read and normalize the current toggle state
2. collect the bounded question and accepted context
3. invoke $consultant
4. return the memo

Consultant output remains non-blocking.