claude-forge

Deep single-model analysis of a topic, question, or architectural decision.

Multi-model consensus workflow. Role-assigned models converge toward a shared recommendation through two rounds of evaluation and reconciliation.

Adversarial multi-model evaluation. Models argue for, against, and neutrally about a subject.

Multi-model panel review. Multiple models review independently, then findings are synthesized.

Full Forge QA checklist in Docker container. Use for release validation or comprehensive verification of all Forge features.

Pressure-test a claim, recommendation, or assumption. Defaults to skepticism.

Review design documents, specs, and technical writing for completeness and consistency.

Review code for conformance, correctness, and architecture alignment.

Read-only Forge installation health check. No writes, no test repo needed.

Explain code, documentation, or technical concepts. Auto-detects code vs docs mode.

Interactive Forge verification walkthrough in a hermetic test environment. Use after installing or upgrading Forge to verify everything works.