xray

Audit Claude Code auto-memory, installed Oracle skills, and session history.

1|Updated May 24, 2026
One-click install
npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill xray-tinner-deinno
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: xray
Source: https://github.com/tinner-deinno/innova-skills-lib/tree/main/core/xray
Command: npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill xray-tinner-deinno

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of not knowing what your AI remembers and which skills are currently installed, making it hard to audit behavior and debug outcomes across sessions.

Core Features & Use Cases

  • Memory X-Ray (auto-memory inspection): Scans Claude Code auto-memory files, highlights stored frontmatter, and reports counts, types, age, and keywords.
  • Memory Operations (read, types, stats, clean, archive): Lets you read specific memory entries, group by type, view detailed statistics, identify stale items, and archive memories safely after confirmation.
  • Skill & Session Visibility: Lists installed Oracle skills with profile/status and shows session history/retrospectives to understand what changed over time.

Use Case: You notice unexpected behavior from the agent and want to confirm which memories reference particular rules or commands, then archive stale or contradictory entries.

Quick Start

Use the xray skill to scan your Claude Code auto-memory and show what the agent currently remembers.

Frequently Asked Questions about xray

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

FAQPage Schema
How do I audit what Claude Code auto-memory remembers across sessions?

To audit Claude Code auto-memory across sessions, scan the project-scoped memory directory to parse stored frontmatter, report counts, types, age, and keywords, and review exactly what the agent currently remembers.

How do I safely archive stale memories from my AI agent?

Safely archive stale memories from your AI agent by scanning auto-memory files, identifying contradictory or aged entries, and archiving them after explicit confirmation without permanently deleting data.

Can I list installed Oracle skills and check session history for debugging?

Yes, you can list installed Oracle skills with profile and status, and display session history or retrospectives to understand agent behavior changes and debug outcomes over time.

What is the best way to inspect agent memory frontmatter and statistics?

The best way to inspect agent memory frontmatter and statistics is to run a deep scan that parses memory files, groups entries by type, and reports detailed memory usage stats.

Why does my AI agent recall outdated rules during debugging?

Your AI agent recalls outdated rules during debugging because stale or contradictory auto-memory entries persist; scanning the memory directory and archiving old frontmatter resolves this uncertainty.

Does memory archiving permanently delete data from the project memory directory?

No, memory archiving does not permanently delete data from the project memory directory; it safely archives memories after confirmation, preserving the ability to resolve agent behavior uncertainty.