refactor: Constitution alignment — reasoning-based rewrites + new skills#20
Merged
refactor: Constitution alignment — reasoning-based rewrites + new skills#20
Conversation
…ased Transform rule-based instructions into reasoning-based per Anthropic Constitution principles. Each constraint now explains WHY it matters, workflows are outcome-driven, and judgment criteria replace rigid templates. commit.md: 2.4/10 → 7+/10 agent-ready-repo-setup: 2.8/10 → 7+/10
System prompt generator that produces reasoning-based prompts from product context. Follows onboarding document structure with identity, goals, constraints with reasoning, and edge case principles. Includes annotated template reference.
Audits system prompts against the Anthropic Constitution's principal hierarchy. Detects operator boundary violations, user protection gaps, and hard constraint conflicts with RED/YELLOW/GREEN severity classification. Includes codified hierarchy rules with Constitution page references.
Restore auth header redaction in agent-ready-repo-setup Pino example. Trim all rewritten files to stay within 20% of original word counts.
Add changelog entries for constitution alignment refactor: - 2 new skills (prompt-as-onboarding, principal-hierarchy-audit) - 2 reasoning-based rewrites (commit.md, agent-ready-repo-setup)
romansklenar
reviewed
Feb 8, 2026
| @@ -0,0 +1,333 @@ | |||
| # Principal Hierarchy Codified Rules | |||
|
|
|||
| This document codifies the principal hierarchy boundaries from Anthropic's Constitution. Use this as a reference when auditing system prompts and plugin configurations for compliance. | |||
There was a problem hiding this comment.
💡 Great to see that somebody is thinking about this! 👍
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Rewrites 2 existing prompt files from rule-based to reasoning-based instructions following Anthropic's Constitutional AI principles, and adds 2 new skills. Part of a cross-plugin constitution alignment effort.
commit.mdfrom step-by-step bash procedures to outcome-driven workflow with judgment criteria (score: 2.4 → 7.4/10)agent-ready-repo-setup/SKILL.mdfrom constraint list to 8 reasoning-based principles with examples and adaptation guidance (score: 2.8 → 8.2/10)prompt-as-onboardingskill — system prompt generator using 8-section annotated templateprincipal-hierarchy-auditskill — hierarchy compliance audit with RED/YELLOW/GREEN classificationreq.headers.authorization)NFR Compliance
Review Findings Addressed
Test plan
bun run validatepasses (v1.9.0)/commitand verify reasoning-based behavioragent-ready-repo-setupskill and verify principle-based outputprompt-as-onboardingandprincipal-hierarchy-auditskills