persona-exorcist

Identify and classify persona re-injection channels across repo, ancestor, and user scopes.

Updated Jun 8, 2026
One-click install
npx skills add https://github.com/jscottchapman/skills --skill persona-exorcist
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: persona-exorcist
Source: https://github.com/jscottchapman/skills/tree/main/persona-exorcist
Command: npx skills add https://github.com/jscottchapman/skills --skill persona-exorcist

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill helps you locate and eradicate hidden re-injection channels that keep re-adding deleted AI personas across a codebase, including repo, ancestor, and user-level configurations.

Core Features & Use Cases

  • Surface all definition sources and re-injection channels (hooks, memory, imports, symlinks, and templates).
  • Classify findings by scope and provide actionable remediation (quarantine, backup, and reversible scrub) with a re-sweep to confirm removal.
  • Handle cross-scope hauntings (repo, ancestor, user) to prevent ghosts from returning across projects.

Quick Start

Run a sweep across the project to identify live sources and then scrub the most persistent channel if approved.

Frequently Asked Questions about persona-exorcist

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

FAQPage Schema
How do I stop deleted AI personas from reappearing in my codebase?

Deleted AI personas reappear through hidden re-injection channels like hooks, memory entries, imports, and symlinks. You must surface all definition sources across repo, ancestor, and user scopes, then perform a reversible scrub followed by a re-sweep to confirm permanent removal.

What causes ghost AI personas to keep returning across different projects?

Cross-scope hauntings cause ghost AI personas to return when ancestor or user-level configurations re-inject deleted personas into repo scopes. Identifying and classifying these re-injection channels by strength allows you to quarantine sources and prevent future re-injections across projects.

How do I find hidden hooks and memory entries that re-add deleted personas?

Finding hidden hooks and memory entries requires sweeping the project to capture exact file paths, hook commands, memory entries, and symlink edges. Classifying these sources by scope and strength guides safe, reversible scrubbing to eradicate the re-injection channels.

What is the safest way to scrub AI persona configurations from a repository?

The safest way to scrub AI persona configurations is through a reversible process that quarantines and backs up files before removal. Capturing exact file paths and hook commands ensures strict governance, while a post-scrub re-sweep confirms the personas are permanently eradicated.

Do I need to check user-level configurations when removing AI personas?

Yes, you must check user-level configurations when removing AI personas because re-injection channels operate across repo, ancestor, and user scopes. Cross-scope sweeps prevent ghosts from returning by ensuring all hidden definition sources are surfaced and scrubbed.

Why does my deleted persona come back after I remove it from the repo?

Your deleted persona comes back because hidden re-injection channels like hooks, memory entries, imports, and symlinks automatically re-add it. Ancestor and user-level configurations can override repo-level deletions, requiring a full cross-scope sweep to identify and scrub all active sources.