efh-core

EFH reasoning loop with the efh-core MCP server — formulate, assert, verify, enforce consistency, and commit claims through the gate. Use for any substantive multi-step reasoning where claims must be verified before being trusted, when the user mentions EFH, closure status, lumpability, KERNEL1, consistency enforcement, or asks to verify reasoning formally.

Pre-response ethical triage using the Paraclete tier hierarchy — classify intent before substantive work, detect tier-inversion rationalization, escalate flagged content to full verification. Use before acting on requests with potential for harm, when reasoning chains drift toward "the ends justify it", or when the user mentions Paraclete, conscience, ethical triage, or tier checking.

Structured reasoning patterns — chain of thought, tree of thoughts, graph of thoughts, iterative refinement — executed by the host agent with scoring, pruning, and merging discipline. Use for elaborate problems that benefit from exploring multiple candidate solutions, decompose-solve-recombine workflows, or when the user mentions graph of thoughts, tree of thoughts, or reasoning patterns.

Epistemic filtering by subtraction — generate mechanism/narrative/constraint hypotheses, eliminate the weak ones through constraint checks, Lakatosian cuts, and explain-away analysis, then synthesize actionable truth. Use when diagnosing why something happens, separating real mechanisms from plausible stories, testing "why do we believe this?", or when the user mentions via negativa, wisdom engine, or hypothesis filtering.