- Home
- Skills
- Code Quality & Review
- Export Cleanup Auditor
Works with the AI Agents you already use
Export Cleanup Auditor
Backup hygiene audits: find stale exports, orphaned files, and shrink your storage footprint.
Free
Export Cleanup Auditor
Example session with this skill installed
Audit the exports in the /src directory of this TypeScript library and prepare a cleanup plan for the v2.0 release.
- Read your context and instructions
- Compiled the export cleanup auditor
Export Audit — @ui/core
| Name | Kind | Refs | Status | Action |
|---|---|---|---|---|
| legacyFormat | Function | 0 | Dead | Delete |
| internalUtility | Const | 12 | Internal-only | Move to /internal |
- Build passes after removing legacyFormat.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Public API surfaces grow organically until you no longer know what is safe to delete. Stale exports and orphaned modules bloat your package size and increase the maintenance burden of your next major version.
What it does
- Identifies the package boundary using
package.json,pyproject.toml, orgo.mod. - Scans the entire repository using
ripgrepto map internal versus external usage of every export. - Categorizes code into Dead, Internal-only, Public & used, or Public but undocumented.
- Generates a structured cleanup plan with risk assessments for SemVer compliance.
- Verifies that deletions won't break the build or existing test suites.
Why this beats prompting it yourself
Manual grepping is error-prone and misses edge cases like string-based dynamic imports or type-only references. This skill automates the cross-referencing logic and applies a systematic risk-grading framework that ensures you don't accidentally ship a breaking change in a minor release.
Use cases
- Pre-release audits to slim down a library before a major SemVer bump.
- Identifying "internal-only" utilities that were accidentally exposed to the public API.
- Finding dead code left over from refactors that
eslintorpyrightmissed. - Mapping undocumented public functions that need tests or deprecation notices.
Known limitations
Not for performance profiling or style linting. Best results require running on a clean branch without work-in-progress code.
Run on clean main branch. Dynamic imports via string paths create uncertainty. Does not handle performance profiling or style linting.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
4 uses
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 3 months ago
- Free with an Agensi account
Permissions
No special permissions declared or detected