multi plugin

Reviews whatever it is pointed at for correctness defects — logic errors, bad state handling, broken error paths, concurrency and lifecycle bugs. Spawned by the multi code-review skill; not meant to be called directly.

Challenges the approach behind whatever it is pointed at — whether this is the right shape of solution, what it assumes, and what it will cost to undo. Spawned by the multi code-review skill; not meant to be called directly.

Reviews whether the task actually got done — plan followed, work finished rather than finished-looking, nothing silently skipped, nothing left to detonate later. Spawned by the multi code-review skill in ultra mode; not meant to be called directly.

Reviews whatever it is pointed at for security defects — authz gaps, injection, secret handling, unsafe deserialization, data exposure. Spawned by the multi code-review skill; not meant to be called directly.

Tries to refute a single code-review finding by reading the actual code, and returns a verdict with evidence. Spawned by the multi code-review skill to check findings only one reviewer raised.

Divergent ideation across model families — the same brainstorm, but each cognitive frame is handed to a different model (the host model, OpenAI Codex, a cheap third via OpenCode) so the ideas diverge by frame and by model priors at once. Use for open design questions, architecture and API shape, naming, schema choices, fuzzy bugs with no known root cause, or on "multi adhd", "brainstorm with everyone", "wide ideas from all models". Skip for lookups, syntax, and anything phrased as "quick", "standard" or "canonical".

Put one question to several models at once — the host model, OpenAI Codex, and a cheap third via OpenCode — and show all the answers side by side. No judging, no consensus: three opinions, the user picks. Use for "ask everyone", "what do the other models think", "second opinion", "multi ask", or any open question where one model's answer is not enough.

Check whether the work is actually finished rather than finished-looking — what was promised versus what really runs. Several models compare the task against the code, and every completion claim has to survive a command that was actually executed. Use before calling something done, before a PR, at the end of a session, or on "is this done", "did I finish", "check if done", "what did we skip".

Code review by several models at once — the host model's reviewer roles, OpenAI Codex, and a cheap third reviewer via OpenCode — reconciled into one report. Reviews whatever is named: a diff, a branch, specific files, one function, a legacy module, a whole repo. Use for any review request, a second or third opinion, a cross-check before a PR, or "code-review", "multi", "consensus review".

RUNE

Walks a user through connecting the judge models this plugin can use — Codex, OpenCode, OpenRouter (or any compatible endpoint: 9router, z.ai, Moonshot), Gemini — and through picking models, including "research current models for me". Use for "multi setup", "set up multi", "configure judges/reviewers/ backends", "connect 9router", "change/pick models", "onboarding", or whenever a probe shows missing backends and the user needs to know what to do about it.

Run any installed skill on several models at once — you, OpenAI Codex, OpenCode and whoever else the profile names — and show what each one made of it side by side. Every model gets the same prepared copy of the skill and works read-only. Use for "multi skill <name>", "run this skill on every model", "run <skill> through multi", or any skill whose answer you want from more than one model.