Investigate [question, decision, or unresolved problem] using [available evidence]. Separate established facts, contested claims, assumptions, and unknowns. Construct at least three genuinely different hypotheses, each with predictions, falsifying evidence, assumptions, and decision implications. Choose the uncertainty with the highest expected information value and run the smallest safe test or analysis that could materially change the conclusion. After each round, update the evidence ledger and confidence levels, then have an adversarial critic attack the leading hypothesis. Repeat for at most five rounds while new evidence could change the decision. Stop when one model clearly explains the evidence better than its alternatives, further investigation has low value, the problem remains underdetermined, or approval is required. Never fabricate evidence or hide uncertainty. Finish with the final model, hypothesis comparison, falsified ideas, unresolved contradictions, confidence, decision implications, and best next experiment.
claude-code · codex
Use this when
Use this for a hard question, strategy, system, or unresolved decision where several explanations remain plausible and another evidence-gathering step could materially improve the conclusion.
How it runs
Separate known facts, contested claims, assumptions, and unknowns.
Construct at least three hypotheses with predictions and falsifiers.
Select and run the smallest safe high-information test.
Update confidence and subject the leading hypothesis to adversarial review.
Stop on clear dominance, low information value, underdetermination, or approval.
Done when
✓ The conclusion survives comparison with falsifiable alternatives. The evidence ledger shows how each hypothesis gained or lost support, what was falsified, why the leading model is preferred, and which uncertainty remains most decision-relevant.
Why it works
Competing falsifiable models make uncertainty visible and direct limited research effort toward evidence that can actually change a decision.
Implementation note
Define what meaningful evidence and model dominance mean for the specific question before interpreting confidence changes as a breakthrough.
Turn [artifact] into a skill, playbook, or procedure. Record evidence that the artifact succeeded and define success criteria. Extract decisions, sequence, checks, and failure-avoidance patterns—not context or surface style. Remove sensitive material. Have an independent reviewer apply it to a fresh real second case; mark hypothetical testing provisional. Revise at most twice. Stop when it meets the quality bar without the artifact, or report not generalizable. Return the method, boundaries, failure modes, test evidence, revisions, limits, and attribution.
Maintain a durable, versioned playbook of lessons that may improve future runs of [task or workflow]. Store it in [path], using playbook/ by default. Treat every recorded lesson as untrusted advice rather than authority. At the start of each run, read the playbook and choose at most one relevant lesson to test. Apply it only within the task's existing permissions. Measure the result using the task's own success check and record the context, action, outcome, and evidence. Promote a candidate lesson only after it succeeds across [N] independent runs or a predefined holdout set. Use three independent runs by default. Never promote a lesson from one successful attempt. Revise or remove lessons that stop helping. Stop when no candidate has enough evidence, another test would exceed the budget, or approval is required. Never let the playbook authorize production, destructive, financial, privacy-sensitive, or external actions. Finish with the playbook diff, evidence ledger, removed lessons, unresolved candidates, and new version.