I traced the agentic calls. Here's where the token consumption comes from

A developer traced the network calls of an agentic coding assistant and found that a simple two-file PyQt edit consumed 3 LLM calls and roughly 760 KB of exchanged JSON, versus a single call and about 100 KB with Aider. After switching part of their workflow to single-shot edits for known files, the developer says their API bill fell from over $400 a month to under $100, and they built a lightweight harness called Frugaast around the single-prompt approach.

I expected an agentic coding assistant to use more tokens than a simpler tool. I didn't expect the difference to be this large. For the exact same simple coding task, I measured: | | Pi | Aider | |---|---|---| | LLM calls | 3 | 1 | | JSON exchanged | ~760 KB | ~100 KB | The task was very simple: a small PyQt project, two files, and a single instruction — "Make the cards width = total width / 3." I already knew exactly which two files needed to be changed. That made me curious about what was actually happening under the hood. My API bill had gone above $400/month, despite trying various techniques to reduce token usage. My company doesn't pay for it, so I wanted to understand where all those tokens were going. I therefore traced the exchanges between a coding harness and the LLM during a simple coding task. To make the test as clean as possible, I used Pi with no add-ons. I explicitly added the two files that needed editing to its context, then compared the result with the exact same prompt in Aider. Here is an overview of the Pi workflow: So you see: for a simple request where I already know what files to edit, there are 3 back and forth with the LLM. The total size of the json files exchanged is 760kB. Not huge, but again this is a very trivial test. The ah-ah moment came when I compared this with the exact same prompt with aider. Here is the aider workflow: Here we have a single LLM call. The first prompt is larger, but contains all the necessary context for the LLM to work. The total size of the json files exchanged is only 100kB Of course, the experiment is excessively simple and fits a case where I already know which files need editing. But in my experience, this is actually the case for a majority of my daily tasks. I don't need an agent to "discover" them and burn tokens in a loop. I just need a tool that applies the edits efficiently. Aider is fantastic for this, but I unfortunately it is not maintained anymore. So I ended up building my own lightweight harness around this exact single-prompt philosophy called Frugaast. By switching part of my workflow away from agentic loops and just using single-shot edits for known files, my API bill dropped from $400+ to under $100 a month. Has anyone else traced their AI editor's network calls? I'm curious if other popular tools like Cursor or Copilot are hiding massive token bloat under the hood.