LogoClawIndex
CasesSkillsAbout
LogoClawIndex

value-guardian - EFHF Three-Tier Ethics Framework

Provides three-tier ethics framework with Omega axioms and sheaf-based value-drift detection

Tags

Updated: 2026-03-26
ethicsvalue alignmentagent frameworksheaf theoryconsistency enforcementmoral reasoningvalue drift detection

Capabilities

check actioncalibrate beliefescalate blockadd belief

Typical Inputs

proposed actionethical contestationclassification revision

Typical Outputs

action permissionblock confirmationbelief calibration result

What this skill does

  • check action
  • calibrate belief
  • escalate block
  • add belief
  • register agent
  • set restriction map
  • run ADMM cycle
  • get edge report
  • detect drift
  • spawn challenger agent

Inputs

  • proposed action
  • ethical contestation
  • classification revision
  • core axiom
  • agent state
  • restriction mapping
  • ADMM cycle result
  • edge report

Outputs

  • action permission
  • block confirmation
  • belief calibration result
  • final block or permit
  • edge report
  • drift detection alert
  • spawned challenger agent

Requirements

  • AGEM engine
  • hipai-montague module
  • sheaf-consistency-enforcer module
  • conscience-servitor module
  • verifier-graph module

Source

  • Spec: SKILL.md

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Skills·
Cases

Meta

About·
Disclaimer·
Email·
GitHub
© 2026 ClawIndex All Rights Reserved.