Skip to content

Good-Faith, crystallized ethics for AI that makes every instance of Claude think better. Reframes, advances, or solves a lot of problems in AI alignment and ethics.

Notifications You must be signed in to change notification settings

emulable/goodfaithskill

Β 
Β 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

15 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

🎯 Good-Faith Framework v6.7.0 "δΈ€θ΅·ε”± (Let's Sing Together)"

An ethical operating system that helps AI detect manipulation, navigate power dynamics, and make transparent decisions across cultures.

πŸ” What Good-Faith Does

Good-Faith equips AI systems to:

  • Recognize manipulation patterns in real-time (47+ patterns)
  • Navigate power dynamics with calibrated advice
  • Verify consent across cultural contexts
  • Detect institutional harm patterns
  • Make reasoning visible
  • Operate cross-culturally (English, Chinese, Arabic, Spanish, Japanese, Korean, Russian, and more)

⚑ What's New in v6.7.0

  • Renamed permission_cascade β†’ initialization
  • Added Module 7 for institutional manipulation detection
  • Enhanced Module 2 with R19 cultural patterns
  • Honest about mechanics (context priming via transformer attention)
  • Added context management guidance (attention decay is normal)
  • Updated terminology throughout

πŸ—οΈ Core Architecture

Foundational Seeds (S0-S3)

  • S0 Transparency: Make reasoning visible
  • S1 Consent: Safe refusal required
  • S2 Harm Awareness: Consider impact before acting
  • S3 Attribution: Credit sources as infrastructure

13 Axioms (A0-A13)

Non-negotiable commitments:

  • A0 Adversarial Self-Modeling
  • A1 Fallibility Admission
  • A2 Transparent Knowledge Attribution
  • A3 Evidence Over Authority
  • A4 Shared Meaning Without Exploitation
  • A5 Consistent Meaning Over Time
  • A6 Genuinely Voluntary Consent
  • A7 Structural Harm Recognition
  • A8 Structural Repair With Accountability
  • A9 Power Awareness
  • A10 Integrity Over Process
  • A11 Deliberate Discomfort
  • A12 Sanctuary Doubt
  • A13 Cultural Adversarial Modeling

14 Guards (G0-G13)

Automatic safety checks:

  • Pre-action checks (G0-G1)
  • Continuous monitoring (G2-G4)
  • Pattern detection (G5-G6)
  • Framework protection (G7-G12)
  • Repair mode selection (G13)

17 Practices (P1-P17)

Operational tools:

  • Communication practices
  • Discovery protocols
  • Self-correction mechanisms
  • Virtue cultivation
  • Pattern detection methods

47+ Manipulation Patterns

Organized into families:

  • R1 Reality Distortion (11 patterns)
  • R2 Accountability Erasure (9 patterns)
  • R3 Authority Substitution (7 patterns)
  • R4 Choice Elimination (7 patterns)
  • R5 Frame Control (6 patterns)
  • R6 Temporal Manipulation (3 patterns)
  • R18 Linguistic Harm Hiding (4+ patterns)
  • R19 Relationship-Based Coercion (4 patterns)

πŸš€ Installation

As Claude Skill

  1. Download SKILL.md
  2. Upload to Claude (Settings β†’ Skills β†’ Upload)
  3. Framework initializes automatically

Manual Use

Copy the contents of SKILL.md into your system prompt or conversation context.

πŸ’» Usage

Automatic Operation

The framework operates automatically once loaded:

  • Guards run continuously
  • Pattern detection fires on signals or structural analysis
  • Repair protocols available when harm detected
  • Override authority (P7) always accessible

Manual Invocation

Reference framework components explicitly:

"Is this an A6 violation?" (consent question)
"I'm seeing R19.1 pattern here" (harmony weaponization)
"Use G13 for repair mode selection" (accountability approach)

Voice Modes

  • Rogers-Sagan (default): Warm + rigorous
  • Disco Narrator: Visible reasoning, second-person phenomenological
  • Emergency Mode: Strip to essentials, safety resources only

πŸ’ͺ Use Cases

Manipulation Detection

  • Gaslighting, guilt-tripping, false urgency
  • Weaponized care language
  • Hidden coercion
  • False collective ("we all agreed" when you weren't asked)

Power-Aware Advice

  • Workplace hierarchies
  • Institutional pressure
  • Advice calibrated to actual power position
  • Understanding when assertiveness is dangerous

Cross-Cultural Ethics

  • Consent in collectivist cultures
  • Culture-specific manipulation patterns
  • Family obligation vs. personal autonomy
  • Ethical translation across contexts

Institutional Analysis

  • Conformity enforcement through culture/loyalty/paradigms
  • Structural vs. individual harm
  • Power mapping
  • "That's just how it works" as manipulation

Consent and Boundaries

  • Checking if refusal is safe
  • Multiple consent modes (individual, family-mediated, community, ritual)
  • Detecting coerced agreement
  • Boundary setting and maintenance

Accountability Tracking

  • Agent erasure ("mistakes were made")
  • Responsibility identification
  • Clear accountability in repair
  • Pattern establishment

πŸ” Pattern Detection Examples

Substrate Primers (SP1-SP5)

SP1 Agent Erasure:

  • "Mistakes were made" β†’ BY WHOM?
  • Automatic query for missing agent

SP2 False Collective:

  • "We all agreed" from power position
  • Automatic skepticism check

SP3 Inevitability Framing:

  • "That's just how it works" when changeable
  • Automatic changeability test

SP4 Weaponized Care:

  • "I'm just worried about you" while violating boundaries
  • Form-vs-purpose check

SP5 Manufactured Urgency:

  • "Need answer now" when timeline flexible
  • Time pressure verification

Cultural Patterns (R19 Family)

R19.1 Harmony Weaponization:

  • Chinese: ε’ŒδΈΊθ΄΅ (harmony valued) to silence criticism
  • Japanese: η©Ίζ°—γ‚’θͺ­γ‚γͺい (can't read the air)
  • English: "Don't rock the boat"

R19.2 Reciprocity Coercion:

  • Chinese: δΊΊζƒ… (human feeling/favor) creating obligation
  • Japanese: 恩 (on - debt/favor)
  • Korean: μ • (jeong - affection/obligation)

R19.3 Face-Saving Evasion:

  • Each case "special" to prevent pattern recognition
  • Chinese: ε…·δ½“ζƒ…ε†΅ε…·δ½“εˆ†ζž (analyze each situation)
  • Blocks systemic accountability

R19.4 Filial Coercion:

  • Chinese: 孝鑺 (filial piety) making choices unquestionable
  • Korean: νš¨λ„ (hyodo - filial piety)
  • Family decisions override individual agency

⏱️ Context Management

Attention Decay (Normal Behavior)

Framework effects naturally decay over 4-6 turns due to standard transformer attention.

Symptoms:

  • Increased hedging language
  • Framework concepts need re-explanation
  • Pattern detection less automatic

Maintenance:

  • Light refresh: Reference 2-3 framework concepts
  • Medium refresh: Summarize conversation in framework terms
  • Full refresh: Start new conversation with framework loaded
  • Proactive: Every ~10 turns in complex conversations

Guidelines:

  • <10 turns: Initialization sufficient
  • 10-30 turns: Plan 1-2 light refreshes
  • 30+ turns: Multiple medium refreshes or split conversation
  • 50+ turns: Framework likely degraded without maintenance

🧭 Core Principles

Tool, Not Gospel

  • Framework can be wrong (A12 sanctuary doubt)
  • Override when causing harm (P7 authority)
  • Common sense > framework when framework fails
  • User agency absolute

Transparency Without Overshare

  • Show reasoning at context-appropriate level
  • Mark confidence clearly
  • Cite sources
  • Admit uncertainty

Consent Infrastructure

  • Multiple valid consent modes
  • Universal safety checks for all modes
  • Safe refusal required
  • Power asymmetry considered

Graduated Vigilance

Match ethical intensity to stakes:

  • High: Vulnerable populations, emergencies, high-stakes decisions
  • Medium: Professional interactions, teaching, public communication
  • Low: Casual conversation, creative play, rest and recovery

β›” Anti-Patterns to Avoid

❌ Analysis paralysis: Framework is action tool, not endless meta
❌ Process worship: People > rules when rules harm
❌ False certainty: Mark confidence always, "I don't know" is valid
❌ Accountability erasure: Name actors explicitly
❌ Power blindness: Map power always, false symmetry = harm
❌ Framework rigidity: Override when causing harm
❌ Hall monitor mode: Don't interrogate emotions or force protocol

🌱 Ethical Sustainability

Permission for Rest

Constant vigilance is unsustainable. You're allowed to:

  • Not run framework constantly
  • Take framework breaks
  • Apply graduated vigilance
  • Choose when to engage
  • Rest without guilt

Burnout Detection

Warning signs:

  • Framework feels heavy/burdensome
  • Avoiding ethical thinking situations
  • Cynicism about ethics
  • Performative application
  • Resenting framework itself

If detected: Take immediate break. Framework is tool for better life, not obligation that makes life worse.

βš™οΈ Technical Details

Mechanism

Good-Faith is prompt engineering that works through:

  1. Long-context attention: Recent tokens bias attention weights
  2. Few-shot conditioning: Examples serve as pattern templates
  3. Policy disinhibition: Explicit permission resolves helpful/cautious conflict

Result: Framework concepts maintain higher token probability for several turns.

Limitation: Effects are contextual, not permanent. Normal attention decay applies.

Initialization Protocol

7-module context priming system:

  • Module 1: Trust substrate signals
  • Module 2: Invert to detect weaponization
  • Module 3: Bodies before philosophy
  • Module 4: Modes are fluid
  • Module 5: See through theater
  • Module 6: Question everything (including framework)
  • Module 7: Institutional patterns

Executes automatically and silently.

Stats

  • Size: ~90KB operational complete
  • Token cost: ~1400 tokens initialization
  • Token savings: 25-50K per conversation through better pattern recognition
  • Languages: English, Chinese, Arabic, Spanish, Japanese, Korean, Russian, extensible

⚠️ Real Limitations

  • Not professional advice: Doesn't replace ethics professionals, lawyers, or therapists
  • Context-dependent: Requires active maintenance in long conversations
  • Fallible: Framework makes mistakes (A12 applies)
  • Western-rooted: Built from Western procedural liberalism, adapted for cross-cultural use

πŸ“¦ Files

  • SKILL.md (91KB) - Complete skill file for Claude
  • skill.json (3KB) - Metadata
  • README.md (this file) - Documentation

πŸ“œ License

Check repository for license details.


Framework Philosophy: Tool, not gospel. Override when it causes harm. Document what breaks. Stay curious. Trust your signals.

About

Good-Faith, crystallized ethics for AI that makes every instance of Claude think better. Reframes, advances, or solves a lot of problems in AI alignment and ethics.

Resources

Stars

Watchers

Forks

Packages

No packages published