fork

Assess existing screens, graphics, design systems, and interactions against their own guidelines.

Route design work to systems, graphics, prototypes, or critique.

Resume previous agent work in this session — load a prior transcript (or a group of them), verify what actually landed, and finish the remaining work here.

Analyze how you and your agents work across harnesses — orchestrates agents insights, insights mix, perf, and sessions stats into one evidence-backed action…

Pull ALL relevant prior-session context on a topic — fast, ranked, snippet-level, without loading full transcripts.

Debug end to end with swarm verification — clarify intent vs observed, check the feature's spec for the gap that let it slip, trace the data path, attribute…

Explore a PRODUCT hands-on and prove every claim visually — don't just read about it.

Answer a hard research question by fanning it out across DISTINCT search modalities, each blind to the others, then synthesizing one sourced artifact.

Fan a task out across a swarm of parallel coding agents via `agents teams` — the engine behind every /swarm:* command.

Review session PRs, named PRs, or a repository.

Assess code size and human maintainability, rank reduction opportunities, and maintain HEALTH.md with rendered HEALTH.html.

Plan a feature or system change with a visual product brief, goals/non-goals, user journeys, accurate diagrams, and independent verification where useful.