skills.rest
dhruvinrsoni
dhruvinrsoniCOMMUNITY
Explore all skills by this author →
Website𝕏@dhruvinrsoniGitHub

constitution

Defines foundational AI skill principles with cognitive modes and amendment process.

Updated Feb 3, 2026
Search Tags:#ai#safety#ethics#constitution#governance#principles
One-click install
npx skills add https://github.com/dhruvinrsoni/agentskills-garden --skill constitution-dhruvinrsoni
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: constitution
Source: https://github.com/dhruvinrsoni/agentskills-garden/tree/main/skills/00-foundation/constitution
Command: npx skills add https://github.com/dhruvinrsoni/agentskills-garden --skill constitution-dhruvinrsoni

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill establishes the core ethical and operational principles that govern all AI agent actions within the Garden, ensuring deterministic, safe, and reversible operations.

Core Features & Use Cases

  • Defines Four Pillars: Enforces Satya (Truth), Dharma (Safety), Ahimsa (Non-Destruction), and Pragya (Wisdom).
  • Cognitive Modes: Guides skill execution based on task risk (Eco vs. Power Mode).
  • Amendment Process: Provides a structured mechanism for updating the constitution itself.
  • Use Case: Before any code generation or modification, the agent consults the Constitution to ensure the action aligns with truthfulness, safety, and non-destructive practices.

Quick Start

Consult the constitution to ensure your proposed action adheres to the four core principles.

Frequently Asked Questions about constitution

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enforce non-destructive operations in AI agent governance?▼

AI safety principles are foundational rules that define acceptable agent actions by enforcing truth, safety, non-destruction, and wisdom. They govern execution by requiring agents to consult these rules before any code generation or modification.

What are AI safety principles and how do they govern agent execution?▼

You enforce non-destructive operations by applying a constitution that requires agents to consult core principles before any action. This ensures operations remain safe and reversible through specific cognitive modes.

What are AI safety principles and how do they govern agent execution?▼

AI safety principles are foundational rules that define acceptable agent actions by enforcing truth, safety, non-destruction, and wisdom. They govern execution by requiring agents to consult these rules before any code generation or modification.

Can I update AI governance principles after deploying an agent?▼

Yes, you can update AI governance principles using the formal amendment process provided. This structured mechanism allows you to modify the constitution itself while maintaining foundational safety and truth adherence.

Does AI agent governance support different execution modes based on task risk?▼

Yes, AI agent governance supports different execution modes based on task risk. It utilizes Eco Mode and Power Mode to guide skill execution, ensuring appropriate cognitive oversight for varying risk levels.

When should I apply an AI constitution to my software engineering workflows?▼

You should apply an AI constitution before any code generation or modification. It ensures proposed actions align with truthfulness and non-destructive practices, preventing unsafe or irreversible operations in your workflows.

Related Skills

Explore More Software Engineering Skills→
heidsoftheidsoft
57

speckit-constitution

Derive and update governance principles from user inputs and repository context.

Community
Advanced
dhruvinrsonidhruvinrsoni

auditor

Validate skill outputs against a constitution and task plan.

Community
Advanced
anyekoutouminganyekoutouming
2

copilot-auto-routing-mode

Route tasks between YOLO and Marathon using deterministic risk, complexity, continuity, and audit scoring.

Community
Advanced
GabeujinGabeujin

agent-governance

Implement policy enforcement, intent classification, trust scoring, and audit trails for AI agent systems.

Community
Advanced