By dhanesh
Evaluate any codebase against 10 Engineering Commandments with 5-level maturity assessment. Generates evidence-backed reports with stack-specific, prioritized actionable improvements.
This skill should be used when the user runs "/commandments", asks to "evaluate the codebase against engineering commandments", "assess engineering maturity", "run a commandments assessment", "check codebase maturity levels", "how mature is this codebase", "engineering best practices audit", "code quality assessment against commandments", or "generate a commandments report". It evaluates the current repository against 10 Engineering Commandments using a 5-level maturity model and generates a detailed report with evidence-backed assessments and stack-specific actionable improvements.
This skill should be ALWAYS ACTIVE during software development. It automatically enforces the 10 Engineering Commandments when the user is writing code, planning features, creating specifications, designing architecture, or reviewing code. Auto-activates on keywords like "implement", "build", "create", "refactor", "design", "architecture", "component", "service", "endpoint", or "module".
A Claude Code plugin that evaluates any codebase against 10 Engineering Commandments using a 5-level maturity model. Generates evidence-backed assessment reports with stack-specific, prioritized actionable improvements.
# From the plugin directory
/plugin install /path/to/engineering-commandments
# Or test locally without installing
cc --plugin-dir /path/to/engineering-commandments
After installation, run /reload-plugins to activate.
/commandments
Run in any repository. No configuration required.
--quick -- Skip WebSearch research phase, use only codebase analysis--focus=NAME -- Deep-dive into a single commandment (e.g., --focus=security)This plugin provides two skills:
enforce-commandments)Automatically enforces the 10 Engineering Commandments during all development activities. A SessionStart hook injects the enforcement skill into your global ~/.claude/CLAUDE.md on first use, ensuring it's always active when writing code, planning features, or reviewing PRs.
/commandments)On-demand codebase maturity assessment:
claudedocs/commandments-report.md with:
| # | Commandment | Key Question |
|---|---|---|
| 1 | Design for Failure | What happens when this fails? |
| 2 | Keep It Simple | Is there a simpler way? |
| 3 | Test Early and Often | How will we test this? |
| 4 | Build for Observability | Can we debug this in production? |
| 5 | Document Thy Intent | Will future-me understand WHY? |
| 6 | Automate Everything Repeatable | Can this be scripted? |
| 7 | Secure by Design | What could be exploited? |
| 8 | Secure Data Consistency | What if the input is garbage? |
| 9 | Separate Concerns | Does this do ONE thing? |
| 10 | Plan for Scale | What happens at 100x load? |
Each commandment is assessed using a 5-level maturity scale (Initial through Optimizing). See commandments.md for the full criteria.
Reports are written to claudedocs/commandments-report.md. The plugin:
claudedocs/ directory if it doesn't existengineering-commandments/
.claude-plugin/
plugin.json # Plugin manifest
marketplace.json # Marketplace installation config
skills/
commandments/
SKILL.md # /commandments assessment skill
enforce-commandments/
SKILL.md # Always-active enforcement skill
hooks/
hooks.json # SessionStart hook config
scripts/
inject-claude-md.sh # Auto-injects enforcement into CLAUDE.md
commandments.md # Bundled maturity criteria (10 x 5 levels)
README.md # This file
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub dhanesh/commandments --plugin engineering-commandmentsConstraint-first development framework with structured phases: initialize, constrain, tension, anchor, generate, verify.
dhaneshAutonomous codebase improvement loop inspired by Karpathy's autoresearch. Iteratively improves code quality, test coverage, performance, and architecture using multi-metric evaluation with diminishing returns detection.
Reference guide for the Twelve-Factor App methodology — 15 principles (12 original + 3 modern extensions) for building portable, resilient, cloud-native applications. Use when evaluating architecture, reviewing codebases for methodology compliance, or advising on configuration, scaling, observability, security, and deployment patterns.
Jamie-BitFlightCode review standards, review culture, quality gates, and automated review infrastructure for tech leads.
sethdfordStructured codebase health attributes with severity-based agent routing
laurigatesAnalyze local repos for code health, complexity, test coverage gaps - multi-dimensional health analysis combining complexity + churn + coverage
jeremylongshoreSkills for development standards: commit messages, code review, testing, documentation, and more. Supports 25 comprehensive skills for the full development lifecycle.
AsiaOstrichAI code reviews grounded in twelve classic engineering books — decay risk diagnostics with book citations, severity labels, and six analysis modes (PR review, architecture audit, tech debt, test quality, health dashboard, full-sweep auto-fix)
hyhmrright