Skill Claude CodeCodex
Evaluate the probability of necessity (PN) for a causal factor — would the conclusion fail if this factor were absent?
not rated 2 2mo ago A 28 tokens
original Apache-2.0
2Stars on the repository
110Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown
Skill Claude CodeCodex
Strategy: Probability of Necessity and Sufficiency (PNS/PS) — systematically evaluate whether each factor is necessary, sufficient, both, or neither for the conclusion.
not rated 2 2mo ago A 40 tokens
original Apache-2.0
Skill Claude CodeCodex
Rate failure mode occurrence probability 1-10. Estimates how likely each failure mode is to manifest during research execution.
not rated 2 2mo ago A 28 tokens
original Apache-2.0
Skill Claude CodeCodex
Identify all parameter dimensions along which a claim's validity might vary.
not rated 2 2mo ago A 18 tokens
original Apache-2.0
Skill Claude CodeCodex
Build a detailed adversarial persona with background, motivation, expertise, blind spots, and preferred attack patterns.
not rated 2 2mo ago A 25 tokens
original Apache-2.0
Skill Claude CodeCodex
Evaluates artifact from a specific assigned perspective. Produces assessment grounded in that viewpoint's values, priorities, and expertise.
not rated 2 2mo ago A 29 tokens
original Apache-2.0
Skill Claude CodeCodex
Execute Klein pre-mortem protocol — assume failure has occurred, generate plausible failure scenarios through prospective hindsight.
not rated 2 2mo ago A 29 tokens
original Apache-2.0
Skill Claude CodeCodex
Tactic: Pre-mortem rapid screening feeds high-risk items into full FMEA analysis. Bridges fast intuitive generation with systematic structured analysis.
not rated 2 2mo ago A 37 tokens
original Apache-2.0
Skill Claude CodeCodex
Execute a single attack probe against an artifact, record the result with evidence and severity classification.
not rated 2 2mo ago A 22 tokens
original Apache-2.0
process-fmea
82Skill Claude CodeCodex
Strategy: Research execution process FMEA — analyzes how the research process itself can fail during execution, distinct from design-level failures.
not rated 2 2mo ago A 29 tokens
original Apache-2.0
Skill Claude CodeCodex
Strategy: Klein pre-mortem — assume the artifact has failed, then retrospect plausible causes. Generates rapid failure scenario catalog.
not rated 2 2mo ago A 30 tokens
original Apache-2.0
re-scoring
84Skill Claude CodeCodex
Re-evaluate S/O/D scores after mitigation measures are in place. Validates that mitigations actually reduce risk as expected.
not rated 2 2mo ago A 29 tokens
original Apache-2.0
Skill Claude CodeCodex
Strategy: Systematic adversarial probing retuned for truth-seeking. Threat surface = the set of load-bearing claims. Output is NOT a resilience score and NOT a hardening list — it is, per claim, the specific observation/computation that would refute it, plus which attacks succeeded. Methods: UFMCS Key Assumptions…
not rated 2 2mo ago A 91 tokens
original Apache-2.0
red-teaming
86Skill Claude CodeCodex
Campaign: Systematic adversarial attack from military/intelligence/AI-safety traditions. Core question: Can systematic adversarial attacks find fatal flaws? Methods: UFMCS Red Team Handbook v9.0, CIA SAT, Anthropic Red Teaming, NIST AI RMF, Inie et al. 12-strategy taxonomy.
not rated 2 2mo ago A 72 tokens
original Apache-2.0
Skill Claude CodeCodex
Strategy: Action Priority matrix — classifies failure modes into H/M/L priority using severity-weighted scoring per AIAG-VDA 2019 Action Priority tables.
not rated 2 2mo ago A 38 tokens
original Apache-2.0
Skill Claude CodeCodex
Rate failure mode severity 1-10 based on end-effect impact. Follows AIAG-VDA severity scale calibrated for research artifacts.
not rated 2 2mo ago A 31 tokens
original Apache-2.0
Skill Claude CodeCodex
Remove one specified factor from the artifact's support structure and reason about how the conclusion changes.
not rated 2 2mo ago A 23 tokens
original Apache-2.0
Skill Claude CodeCodex
Strategy: Multi-agent collaborative debate based on Du et al. Society of Mind. Agents share perspectives iteratively until convergence or divergence is detected.
not rated 2 2mo ago A 34 tokens
original Apache-2.0
Skill Claude CodeCodex
Strategy: Military-grade assumption testing — Key Assumptions Check, Devil's Advocacy, Team A/B analysis to expose hidden dependencies and unexamined beliefs.
not rated 2 2mo ago A 38 tokens
original Apache-2.0
Skill Claude CodeCodex
Tactic: Progressive debate escalation based on confidence thresholds. Each round increases attack sophistication until defender collapses or proves resilient.
not rated 2 2mo ago A 33 tokens
original Apache-2.0
Skill Claude CodeCodex
Paper landscape scan returning abstracts and metadata. Import of literature-engine/paper-overview skill. Abstracts only — no conclusions from abstracts.
not rated 2 2mo ago A 33 tokens
original Apache-2.0
Skill Claude CodeCodex
Paper full text access via alphaxiv answerpdfqueries or getpapercontent(fullText=true). Import of literature-engine/paper-research skill. Raw extracted text for precise claims.
not rated 2 2mo ago A 43 tokens
original Apache-2.0
Skill Claude CodeCodex
Paper AI summary report via alphaxiv getpapercontent. Import of literature-engine/paper-search skill. Structured AI-generated intermediate report.
not rated 2 2mo ago A 33 tokens
original Apache-2.0
Skill Claude CodeCodex
Tactic: Sequential perspective evaluation with divergence aggregation. Each agent evaluates from a distinct viewpoint, then disagreements are surfaced and resolved.
not rated 2 2mo ago A 32 tokens
original Apache-2.0
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: