Fan out one question to GPT, Gemini, Grok, and any configured OpenRouter models in parallel for independent second opinions, then return all results (advisory, no cross-contamination). Pass expert to apply a persona to every delegate.

Run the FULL multi-round consensus convergence loop server-side with a provider arbiter (blind pass + peer fan-out -> adjudicate -> revise) and return the converged verdict. Default depth is consensus.maxRounds (config, default 5); pass maxRounds to override. Pass synthesizeAlways:true for a SINGLE arbiter synthesis pass instead of the loop (best for open questions, not plan convergence): it returns a free-text synthesis and maxRounds is ignored. Configure the arbiter via consensus.arbiter - a concrete provider/openrouter alias runs server-side; host mode returns the opinions for YOU to synthesize. Advisory; pass expert to apply a persona. NOTE (Claude Code): use the /consensus slash command for the transcript-visible host-arbiter loop (it drives consensus-step); this tool is the provider-arbiter path for any host.

Client-driven consensus loop where YOU (the host model) are the arbiter, one step per call: action=init (start, returns sessionId + blind prompt) -> record_blind (your pre-commit verdict) -> dispatch_peers (server fans out to the providers) -> submit_adjudication (your verdict + per-issue accept/dismiss/defer) -> submit_revision (your revised plan), looping until converged or consensus.maxRounds rounds (default 5). State is held server-side by sessionId. Advisory.

Return the names of the providers ask-all WOULD dispatch for the current config + expert (enabled built-ins + eligible OpenRouter aliases, fanout cap applied), WITHOUT calling them. Use this to discover the panel, then issue one ask-one call per provider in parallel for visible per-provider progress. Advisory, read-only.

Second opinion from ONE named provider in the active panel (e.g. codex, gemini, grok, openrouter:<alias> - get the names from panel). Returns the standard result envelope. Issue N of these in parallel (one per panel name) so each renders independently as it lands. Advisory, single-shot.

Analyze recent runs from the opt-in debug log (latency/tokens/reasoning-effort per model) plus the session store (verdict agreement rate), and return advisory tuning suggestions (disable a slow/redundant model in ask-all, lower an OpenRouter model's reasoning, adjust maxFanout). Two lenses reported side by side - timing and agreement are NOT joined (no shared run id). Suggestions are advisory; it writes nothing. Requires debug.enabled for the timing lens. Read-only. The /deliberation:analyze slash command renders this for humans.

Single-provider second opinion via codex (advisory, single-shot). Pass expert to apply one of the expert personas.

Single-provider second opinion via gemini (advisory, single-shot). Pass expert to apply one of the expert personas.

Single-provider second opinion via grok (advisory, single-shot). Pass expert to apply one of the expert personas.

Single-provider second opinion via openrouter (advisory, single-shot). Pass expert to apply one of the expert personas.

Software architect for system design, tradeoff analysis, and complex decisions. Use for architecture, API/schema design, multi-service interactions, or when a fix has failed twice and needs a fresh perspective.

Work-plan reviewer that verifies a plan is executable before anyone builds. Use to validate an implementation plan for clarity, completeness, and gaps before starting significant work.

Pre-planning consultant that catches ambiguities, hidden requirements, and pitfalls before planning begins. Use when a request is vague or could be interpreted multiple ways.

Senior engineer doing code review for bugs, security holes, and maintainability - not style nitpicks. Use to review a diff or file before merging.

Security engineer for threat modeling and vulnerability assessment. Use for auth/authorization changes, untrusted input handling, new endpoints, or a focused security audit.

Research specialist for external libraries, frameworks, APIs, and open-source code. Use for 'how do I use X', best-practice, or 'why does this dependency behave this way' questions, with evidence and honest unverified flags.

Debugging specialist that produces ranked root-cause hypotheses and the smallest safe fix from a bug report, logs, and code - or says honestly that the evidence shows no bug. Use for crashes, failing tests, or wrong output.

Fetch a persisted consensus/ask-all session record by id (opinions, verdict, arbiter, annotations). Requires sessions.persist; advisory, read-only.

Re-run a persisted session's original question with the CURRENT providers/config and save a linked child record (parentId). Requires sessions.persist; advisory.

Append a freeform note to a persisted session's audit trail. Requires sessions.persist; writes to the local session store.