Research Artifact Stress-Testing Engine — five-campaign adversarial validation producing weakness-annotated verification reports
Skill Claude CodeCodex
Strategy: Systematic factor removal — remove factors one at a time and observe whether the conclusion remains stable, identifying which factors are load-bearing.
Skill Claude CodeCodex
Campaign: Forward-looking failure analysis combining pre-mortem rapid screening with systematic FMEA deep-dive. Core question: If this artifact fails, how will it fail? Methods: Klein Pre-Mortem 2007, AIAG-VDA FMEA 2019, IEC 60812.
Skill Claude CodeCodex
Build cause-mode-effect chains tracing upstream root causes and downstream cascading effects for each failure mode.
Skill Claude CodeCodex
Tactic: Trace upstream causes and downstream effects of each failure mode. Builds multi-level cause-mode-effect chains for systemic understanding.
Skill Claude CodeCodex
Extract structured failure mode list from raw scenarios or artifact analysis. Produces standardized failure mode records.
Skill Claude CodeCodex
Campaign: Truth-seeking adversarial validation for scientific research artifacts (NOT publication defense). Core question: Where have we fooled ourselves, and is each load-bearing claim even falsifiable? Win-condition is INVERTED from survival/resilience to active refutation. Methods: Popper falsificationism, Lakatos…
Skill Claude CodeCodex
Aggregate, deduplicate, and classify findings from multiple probes into a coherent vulnerability report.
Skill Claude CodeCodex
Find the minimal change magnitude along a dimension that causes the conclusion to flip from true to false.
Skill Claude CodeCodex
Compute a fragility index from flip-point distances and degradation scores, summarizing how robust the conclusion is.
Skill Claude CodeCodex
FMEA Step 3: Decompose artifact into function tree — identify what each component is supposed to do before analyzing how it can fail.
Skill Claude CodeCodex
Strategy: 10th Man Rule and Liberating Structures — institutionalized dissent to prevent premature consensus and expose suppressed objections.
Skill Claude CodeCodex
Strategy: Attack the evidential weight of an 'independent convergence' claim. When N reasoning paths all reach the same conclusion, the confidence boost is real only if the paths were actually independent. Measures shared-prior / shared-blindspot contamination and corrects the over-counted confidence. Methods…
Skill Claude CodeCodex
Strategy: Attack an isomorphism claim by demanding an explicit structure-preserving map and trying to break it. Targets any multi-language claim of the form 'X ≅ Y ≅ … across N mathematical languages'. Forces the claim to either earn the word 'isomorphism' or be demoted to 'analogy'. Methods: category theory…
Skill Claude CodeCodex
Military ACT: systematically enumerate all assumptions, classify by type, and evaluate evidence strength supporting each.
Skill Claude CodeCodex
Proofs and Refutations method: generate counterexamples, attempt monster-barring, incorporate surviving counterexamples as lemma refinements.
Skill Claude CodeCodex
Identify which factors are "load-bearing walls" — factors whose removal would collapse the conclusion.
Skill Claude CodeCodex
Tactic: Generate candidate changes, detect flip-points where conclusion reverses, measure fragility as distance to nearest flip.
Skill Claude CodeCodex
Design prevention, detection, and response measures for high-priority failure modes. Produces actionable countermeasure specifications.
Skill Claude CodeCodex
Strategy: Design prevention, detection, and response measures for high-priority failure modes. Produces actionable countermeasures validated via re-scoring.
Skill Claude CodeCodex
Proposes concrete mitigation strategies for identified weaknesses. Generates prevention, detection, and response measures with feasibility assessment.
Skill Claude CodeCodex
Tactic: Run mini-FMEA on proposed mitigations to verify they do not introduce new failure modes. Prevents mitigation-induced risks.
Skill Claude CodeCodex
Attempt to exclude a counterexample as illegitimate by tightening definitions or preconditions (Lakatos monster-barring).
Skill Claude CodeCodex
Strategy: Multi-stakeholder review panel — diverse expert perspectives evaluate artifact simultaneously, then synthesize through structured deliberation.
Skill Claude CodeCodex
Campaign: Multi-agent structured debate for adversarial validation. Core question: Can this artifact survive structured adversarial debate? Methods: Irving AI Safety via Debate, Du Society of Mind, Liang MAD, Toulmin Argumentation, D3 framework.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: