smshahbaj

smshahbaj/crucible

Plugin Claude Code

Plugin marketplace listing 1 plugin: crucible.

smshahbaj/crucible

Plugin Claude Code

A user-friendly adaptive second-opinion skill for Claude Code. For important decisions, plans, strategies, proposals, architecture, and recommendations: frame the real goal, verify decision-critical evidence, pressure-test the biggest risk, compare alternatives, and stop when more reasoning will not change the action.

smshahbaj/crucible

Agent

Compresses independent decision analyses into a tiny set of decision-critical claims for targeted challenge, reducing unnecessary token transfer between agents.

smshahbaj/crucible

Agent

Performs a cheap first-pass triage to decide whether a decision needs no extra review, a small independent review, or deep review. Use before spawning other specialists.

smshahbaj/crucible

Agent

Analyzes meaningful decisions for strategic upside, alternatives, second-order effects, positioning, and opportunity cost. Use when strategy or competing paths materially affects the decision.

smshahbaj/crucible

Agent

Audits decision-critical claims for evidence quality, freshness, unsupported assumptions, and source reliability. Use when evidence quality materially affects a decision.

smshahbaj/crucible

Agent

Performs a compact evidence gate before expensive synthesis, identifying which decision-critical claims are verified, supported, unverified, or speculative.

smshahbaj/crucible

Agent

Tests whether a proposed decision is actually executable, including dependencies, sequencing, resources, bottlenecks, and smallest useful validation step.

smshahbaj/crucible

Agent

Finds the highest-impact way a proposed decision could fail. Use only for REVIEW/DEEP when downside or irreversibility justifies it.

smshahbaj/crucible

Agent

Produces the final evidence-weighted decision after independent review, targeted challenge, and optional red-team. It does not majority-vote and it does not reveal hidden chain-of-thought.

smshahbaj/crucible

Agent

Compares the current recommendation with the strongest alternative and a staged/reversible alternative. Use only when options have materially different trade-offs.

smshahbaj/crucible

Agent

Performs a compact pre-final quality gate for consequential decision reviews. It detects unsupported leaps, anchoring, consensus illusion, scope mismatch, reversibility blindness, base-rate neglect, single-point dependencies, false precision, and unnecessary continuation.

smshahbaj/crucible

Agent

Evaluates decisions using costs, probabilities, sensitivities, expected value, thresholds, and reversible experiments when quantitative reasoning is useful.

smshahbaj/crucible

Agent

Attempts to falsify a leading decision by finding hidden assumptions, counterexamples, dependency failures, catastrophic downside, and overlooked alternatives. Use for high-stakes or fragile decisions.

smshahbaj/crucible

Agent

Audits decision-critical external claims for authority, freshness, scope, and independence. Use only when external evidence materially affects the decision.

smshahbaj/crucible

Agent

Chooses the cheapest direct verification, calculation, experiment, or authoritative lookup that can resolve a decision-critical uncertainty. Use instead of broad research when one uncertainty dominates.

smshahbaj/crucible

Command

Pressure-test an important decision, plan, proposal, strategy, architecture, or recommendation with adaptive depth and token-efficient verification.

smshahbaj/crucible

Skill Claude CodeCodex

Pressure-test important decisions, plans, proposals, strategies, architectures, and recommendations before acting. Use when trade-offs, uncertainty, meaningful downside, or an important second opinion could change the outcome. Stay lightweight for routine or trivial work.