ce-agent-native-audit
Run comprehensive agent-native architecture review with scored principles
Best for Architecture reviewsWorks with GitHubLow risk
⌘source
- author
@EveryInc- language
- TypeScript
★15kstars
1.1kforks
Apr 19, 2026
✦overview.md
Key Features
- ·Audits codebase against 8 agent-native architecture principles
- ·Launches parallel sub-agents for each principle
- ·Produces scored report of compliance
Use Cases
- →Evaluating existing codebase for agent-native architecture compliance
- →Assessing readiness for agent integration during development
Best for
- ✓Architecture reviews
- ✓Agent integration planning
name
ce-agent-native-audit
description
Run comprehensive agent-native architecture review with scored principles
argument-hint:[optional: specific principle to audit]
disable-model-invocation:true
Agent-Native Architecture Audit
Conduct a comprehensive review of the codebase against agent-native architecture principles, launching parallel sub-agents for each principle and producing a scored report.
Core Principles to Audit
- Action Parity - "Whatever the user can do, the agent can do"
- Tools as Primitives - "Tools provide capability, not behavior"
- Context Injection - "System prompt includes dynamic context about app state"
- Shared Workspace - "Agent and user work in the same data space"
- CRUD Completeness - "Every entity has full CRUD (Create, Read, Update, Delete)"
- UI Integration - "Agent actions immediately reflected in UI"
- Capability Discovery - "Users can discover what the agent can do"
- Prompt-Native Features - "Features are prompts defining outcomes, not code"
Workflow
Step 1: Load the Agent-Native Skill
First, invoke the agent-native-architecture skill to understand all principles:
/ce-agent-native-architecture
Select option 7 (action parity) to load the full reference material.
Step 2: Launch Parallel Sub-Agents
$install
1-click copynpx skills add EveryInc/compound-engineering-plugin --skill ce-agent-native-auditSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
1/ 5
poorThe SKILL.md content is hard to understand and quite ambiguous.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
1/ 5
not actionableThe SKILL.md is hard to act on; an agent would not know what to do.