AI Attic Doctor: Optimize and Secure Your .attic/ Contents

AI Attic Doctor: Optimize and Secure Your .attic/ Contents

The AI Attic Doctor is an AI agent skill designed to inspect and maintain the health of the .attic/ directory. It identifies issues such as orphaned items, stale index lines, malformed frontmatter, oversized hooks, and potential credential leaks. This tool facilitates developers and teams in achieving organized and secure attic contents without delving into merge or conflict issues typically handled by attic-git.

What this skill does

• Checks for inconsistencies in the .attic/ directory, like missing or stale index lines and orphaned item files.
• Identifies and corrects malformed frontmatter in item files according to specified format guidelines.
• Highlights and advises on oversized hooks exceeding 100 characters for improved session efficiency.
• Detects potential credential leaks, prompting users to rotate and remove the credentials from files.
• Generates a validation report that signals the health status of the .attic/ directory, utilizing exit codes to indicate issues.
• Guides users in executing corrections through specific commands, such as `attic.js rebuild` to regenerate the index.

Who it is for

This skill is suitable for developers and engineering teams utilizing AI coding agents like Claude Code, Cursor, and Codex. It is particularly useful for those who need to ensure the integrity and security of their attic content on a regular basis.

Use cases

• Routine maintenance checks of the .attic/ directory for development teams to prevent data drift and maintain optimal directory health.
• Security audits to identify and mitigate credential leaks before the .attic/ directory is committed to version control systems.
• Document integrity checks for developers looking to maintain well-structured and correctly formatted data in their projects.

Technical details

• Implemented with JavaScript, utilizing a script located through a specific shell command to ensure the latest version availability.
• Integration with AI coding platforms: Claude Code, Cursor, and Codex, enabling seamless execution of routine maintenance tasks.
• Operation triggered by specific verbal commands, aligning with intuitive user workflows for enhanced usability.

For authorised security testing, defensive research and educational use only.

Source & Licence

This package is built on open-source work published by NishikantaRay (NishikantaRay/Attic) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.