Back to Skills

authoring-constitution

verified

Use when creating or updating project constitution, when user asks to "write principles", "define governance", or mentions "constitution", "governance", "principles", "enforcement", or "amendment process". Core skill for greenfield projects.

View on GitHub

Marketplace

humaninloop-plugins

deepeshBodh/human-in-loop

Plugin

humaninloop

Repository

deepeshBodh/human-in-loop
9stars

plugins/humaninloop/skills/authoring-constitution/SKILL.md

Last Verified

January 25, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/deepeshBodh/human-in-loop/blob/main/plugins/humaninloop/skills/authoring-constitution/SKILL.md -a claude-code --skill authoring-constitution

Installation paths:

Claude
.claude/skills/authoring-constitution/
Powered by add-skill CLI

Instructions

# Authoring Constitution

## Overview

Write project constitutions that teams actually follow. Every principle must be enforceable, testable, and justified. Vague aspirations are rejected in favor of actionable constraints with measurable criteria.

## When to Use

- User asks to "create a constitution" or "define governance"
- Starting a new greenfield project that needs governance
- User wants to "write principles" or "define constraints"
- Establishing quality gates and enforcement mechanisms
- Defining amendment processes and version policies

## When NOT to Use

- **Brownfield projects with existing code**: Use `humaninloop:brownfield-constitution` instead, which provides Essential Floor + Emergent Ceiling approach
- **Reviewing an existing constitution**: Use `humaninloop:validation-constitution` for quality checks
- **Syncing CLAUDE.md after constitution changes**: Use `humaninloop:syncing-claude-md` for synchronization

## Common Mistakes

| Mistake | Problem | Fix |
|---------|---------|-----|
| Vague principles | "Code should be clean" has no enforcement | Add specific, measurable criteria: "Functions MUST be ≤40 lines" |
| Missing enforcement | Principles without verification become suggestions | Every principle needs CI automation, code review checklist, or audit process |
| Untestable criteria | "Good architecture" can't be verified | Define binary pass/fail: "No domain imports from infrastructure layer" |
| No rationale | Future maintainers don't know why rules exist | Explain the failure mode prevented and success enabled |
| Skipping SYNC IMPACT | Constitution changes without audit trail | Always update the SYNC IMPACT REPORT header with version changes |
| CLAUDE.md drift | AI assistants operate with outdated guidance | Include CLAUDE.md Sync Mandate section; update both files together |

## The Three-Part Principle Rule

Every principle MUST have three components. A principle without all three is incomplete and should not be accepted.

### 1. Enfor

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
11824 chars