I Built a Tool Because 90% of My AI Agent's Tokens Were Spent Searching, Not Coding

5,000 to 10,000 tokens. That's what my AI agent was burning before changing a single line of frontend code. I started paying attention to this a while back. I'd ask the agent to do something small ("fix the padding on that card," "swap this to the secondary variant") and the actual edit would be maybe 200 tokens of real work. But the agent wouldn't start with the edit. It would start with a search. Grepping the codebase, reading five files, asking me "is this the right component?", reading more files, building more context. All of that before it touched a line of code. And the thing that kept bugging me wasn't the token cost itself; it was what the token cost was doing to my iteration speed. I work in fast loops. Change something, see the result, change something else. That's how frontend development is supposed to feel. But when every small UI tweak comes with a 30-second search phase and thousands of tokens of overhead, those fast loops turn into slow, expensive ones. The worst part