forge-council

Convene a council of independent AI CLI harnesses (codex, agy, grok, Lumo) plus a Fable subagent to review ONE artifact in parallel, then synthesize by cross-harness agreement. USE WHEN you want a second and third opinion from other vendors on a repo, PR, plan, findings, spec, or design; running an adversarial cross-check across models; stress-testing a decision; or figuring out which CLI harnesses can actually run headlessly and how to handle their quirks (hangs, preamble-only output, missing CLIs, drifted model ids).

Convene a research council — 3-round debate where specialists with different epistemic stances investigate a topic and challenge each other's findings. USE WHEN deep multi-perspective research, evaluating evidence quality, controversial or uncertain topics, strategic intel-gathering before a decision, surveying a landscape across vendor / academic / community sources, or when a single-pass ResearchTopic skill won't pressure-test findings hard enough.

Convene a PAI-style council — 3-round debate where specialists challenge each other. USE WHEN multi-perspective discussion, architecture debate, strategy decisions, cross-domain analysis.

Convene a developer council — 3-round debate for code review, architecture, and debugging. USE WHEN multi-perspective code review, architecture decisions, team-based problem solving, developer council.

Convene a hiring council -- multi-agent review of job postings, role definitions, and hiring strategy. USE WHEN job posting review, role design, hiring decisions, compensation review, recruitment strategy.

Convene a knowledge management council — 3-round debate on vault organization, memory lifecycle, note architecture, and skill design. USE WHEN knowledge triage, memory promotion, vault organization, note lifecycle, idea graduation, archive decisions.

Convene a product council — multi-agent review of requirements, features, and product strategy. USE WHEN requirements review, feature scoping, product decisions, go/no-go, payments review.