Check a codebase for redundant packages and polyfills
An agent can scan code and install commands to find dependencies that can be replaced with built-ins or better options.
- What they did
- A developer connected the e18e MCP server to their agent, either through a remote HTTP setup or by using the local @e18e/mcp package. After that, the agent could review install commands, inspect source files for import substitutions, search by package name or topic, and open migration guides.
- How it went
- The setup description does not show a real audit result, so there is no evidence of how many packages were flagged or removed. It also notes that the checker handles one source file at a time, which means a full repository needs file-by-file review.
- Tips
- Use it as a review tool, not an auto-fixer. Ask the agent to pause before any changes to package files or installs, and have it work through the repo one file at a time.
Try it yourself with Claude Code
Review the code at [repo path] for dependencies and polyfills that look unnecessary in [runtime/version]. Check install commands, source imports, and any obvious built-in replacements. List each item with the current package, why it seems redundant, and a safer replacement; then stop and ask me to approve before you change any package files, delete anything, or run installs.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Let your agent patch its own repo
A developer reported that their custom agent made its first code edit in its own repository.
Create a fast phone agent with live voice streaming
They assembled a call-answering agent with live transcription, generation, and speech output, then moved it closer to the services to get about 400ms latency.
Review Linux kernel patches before they land
Google’s Sashiko scans Linux kernel submissions and flags bugs that human reviewers missed.
Create a CLI coding agent from a Python LLM base
Claude Code turned Simon Willison’s Python LLM template into a working CLI coding agent from two prompts.
Review a feature and pass the findings to an engineer
One developer had an agent inspect a feature for problems, then handed the issue list to an engineer whose agent fixed most of them.
Trace C# symbol usage with a Roslyn-backed index
Graphify C# helps agents map real C# usages, including overrides and implementations, from compiler-resolved project data.