ce-agent-native-audit

Audit codebase architecture against agent-native principles and generate scored reports.

Updated Apr 26, 2026
One-click install
npx skills add https://github.com/DieStok/ridder_lab_retreat_ai_hackathon_2026 --skill ce-agent-native-audit-diestok
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ce-agent-native-audit
Source: https://github.com/DieStok/ridder_lab_retreat_ai_hackathon_2026/tree/main/.agents/skills/compound-engineering/skills/ce-agent-native-audit
Command: npx skills add https://github.com/DieStok/ridder_lab_retreat_ai_hackathon_2026 --skill ce-agent-native-audit-diestok

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Identifies gaps in how codebases implement agent-native architecture by evaluating a set of core principles and producing a scored, actionable report.

Core Features & Use Cases

  • Parallel principle audits across Action Parity, Tools as Primitives, Context Injection, Shared Workspace, CRUD Completeness, UI Integration, Capability Discovery, and Prompt-Native Features.
  • Generates a per-principle score and concrete recommendations to guide remediation.
  • Suitable for large codebases with multiple agents and tooling to improve architecture governance.

Quick Start

Run /ce-agent-native-architecture to load the agent-native architecture audit workflow.

Frequently Asked Questions about ce-agent-native-audit

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

FAQPage Schema
How do I audit my codebase for agent-native architecture compliance?

An agent-native architecture audit analyzes your codebase against core principles like Action Parity, Context Injection, and CRUD Completeness to surface compliance gaps, generating per-principle scores and concrete improvement recommendations.

What is agent-native architecture and when do I need an audit?

Agent-native architecture structures codebases around principles like Tools as Primitives, Shared Workspace, and Capability Discovery. You need an audit when managing large codebases with multiple agents, prompts, and data stores to ensure proper architecture governance and identify compliance gaps.

How do I score agent-native principles across a large multi-agent codebase?

Scoring agent-native principles across a large codebase requires running parallel audits across eight specific principles including Action Parity, Tools as Primitives, and Prompt-Native Features. The audit generates a structured report with per-principle scores and prioritized remediation actions.

Can I audit codebases with multiple agents and data stores for architecture gaps?

Yes, you can audit large codebases containing multiple agents, prompts, and data stores. The audit evaluates agent-native principles in parallel, producing a human-readable report that highlights strengths, gaps, and concrete recommendations to improve architecture governance.

What's the best way to generate improvement recommendations for agent-native architecture gaps?

The best way to generate improvement recommendations is running a parallel principle audit across Action Parity, Context Injection, and CRUD Completeness. This produces a structured, human-readable report with per-principle scores and prioritized actions for remediation.

What limitations should I expect when auditing agent-native architecture in complex codebases?

When auditing agent-native architecture in complex codebases, limitations may arise if the repository lacks multiple agents, prompts, or data stores. The audit is designed for large codebases requiring architecture governance, so smaller projects may yield less actionable per-principle scores and recommendations.