detect-pass-by-construction

SkillDev tools

Lets your agent spot when a review or test is set up so it cannot fail because it shares assumptions with the claim it checks.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the detect-pass-by-construction skill

About this skill

Identify cases where the validator is structurally unable to reject the target because acceptance follows from assumptions copied from the target theory or construction process.

What this skill tells your AI

The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/detect-pass-by-construction/SKILL.md and read by ahel’s review.

Purpose

Identify validators structurally unable to reject a target because acceptance follows from copied assumptions.

Input contract

required: [target_claim, validator, noncircularity_matrix]
optional: [acceptance_rule, construction_history]
constraints: [copied, shared, derived, and independent assumptions must be distinguished]

Procedure

  1. Find validator assumptions copied from the target.
  2. Trace whether acceptance follows without an independent test.
  3. Report pass-by-construction and required failure channels.

Output contract

produces: [pass_by_construction_finding, copied_assumptions, missing_failure_channels]
delta_fields: [findings, evidence_updates, uncertainties, decisions]

Quality gates

  • A finding requires an explicit dependency path from target assumption to acceptance rule.

Failure and counterexamples

Do not call shared domain knowledge circular without tracing how it enters acceptance.

Provenance map

  • resolved: circular-validation-audit

Signals

GitHub stars
501
Forks
41
Last commit
Sep 2026
Advanced
Catalog kind
skill
Key
detect-pass-by-construction
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine