TorpedoD

Collects evidence from web sources (Crawl4AI) and local documents (Docling), applies quarantine classification, deduplication, and provenance tagging.

Claim-sliced report composer for research Phase 6. Writes canonical output/report.md from section briefs and claim slices; publishing renders optional formats later.

Orchestrates multi-phase research pipeline: scoping, evidence collection, claim extraction, graph relationship enrichment, section brief synthesis, report composition, and publishing.

Extracts canonical claims from collected evidence, enriches them with compact graph relationship metadata, and produces section briefs plus per-section claim slices for report composition.

Convene a structured LLM Council — five thinking-lens advisors (Red Team, First Principles, Expansionist, Outsider, Executor) plus anonymised peer review, forced debate on consensus, dual-chairman synthesis with dissent preservation, and optional Codex-powered Decision Science pass — to pressure-test high-stakes decisions. Adaptive modes (Quick/Standard/Deep) keep cost bounded; a persistent journal enables learning across runs. Mandatory triggers: /claude-council, "convene the council", "run this by the council", "I need the council", "council this", "pressure-test this", "stress-test this", "war room this", "debate this". Strong triggers: "I'm torn between X and Y", "this is a big decision", "help me think this through from multiple angles", "I need outside perspectives", "should I X or Y" (with real stakes — if binary with obvious answer, triage rejects per Step 1 rule 4). Do NOT invoke for factual questions, coding help, debugging, quick yes/no decisions, emotional support, or questions with one right answ