AgenticArchitect OS eligible

Refactor Agent

Takes a refactoring goal, analyzes impact, plans changes, executes safely, verifies no regressions. Includes post-refactor anti-hallucination verification for import paths, barrel exports, test references, and pattern consistency.

How to activate

Say any of these phrases in your IDE to trigger this skill:

“refactor”“clean up”“restructure”“extract component”

Run via CLI

enterprise-skills run refactor-agent

Aliases:

refactorclean-uprestructurereorganize

Relationships

Depends on:

Governance Enforcement

Enforces Pre-Code Gate, model roles, preflight resolution, mid-session handoff, execution logging, and feedback capture. Reads .project-ai/ authority pack when available.

Coordinates with:

Test Orchestrator

Unified test execution and coordination agent. Detects test infrastructure, runs suites across languages, interprets results, identifies coverage gaps, and coordinates with bootstrap-testing and uat-workflow-crawler.

Code Review

Enterprise code review on recent changes or GitHub PRs. Checks standards, anti-patterns, error handling, type safety.

Anti-Hallucination Agent

Deep anti-hallucination verification aligned with Anthropic and OpenAI best practices. Cross-reference validation, code grounding checks, capability claim verification, RAG grounding, and refactor integrity analysis. Three-layer enforcement: baseline governance, code generation guards, and on-demand deep audit.