---
title: "Comment by Vlad Zoff on \"My AI coding agent kept grepping my repo to find one function — so I cut its token usage by 90%\" | Hashnode"
description: "Token reduction is a good start, but I'd also test retrieval quality after a symbol is renamed or moved across modules. An index that returns fewer tokens but p"
url: "https://hashnode.com/posts/ai-agent-codebase-indexer-skill-spelunk/6a609b9ba874e83d3cbc81e5/comment/6ae20a3277d5cbaa0c48c1bc"
---

[Discussion](https://hashnode.com/posts/ai-agent-codebase-indexer-skill-spelunk/6a609b9ba874e83d3cbc81e5)

Comment [My AI coding agent kept grepping my repo to find one function — so I cut its token usage by 90%](https://hashnode.com/posts/ai-agent-codebase-indexer-skill-spelunk/6a609b9ba874e83d3cbc81e5)

[Vlad Zoff](https://hashnode.com/@vladzoff)

[Oct 28](https://hashnode.com/posts/ai-agent-codebase-indexer-skill-spelunk/6a609b9ba874e83d3cbc81e5/comment/6ae20a3277d5cbaa0c48c1bc)

Token reduction is a good start, but I'd also test retrieval quality after a symbol is renamed or moved across modules. An index that returns fewer tokens but points to stale locations can make the agent confidently edit the wrong implementation. Measuring recall on a small set of real repo questions would help show whether the savings are actually useful.
