Cline · Updated 2026-10-09
Reduce Cline, Roo Code and Kilo Code Token Usage
Cline, Roo Code and Kilo Code send the task history with each request, and that history fills up with file reads, terminal output and MCP results. Here is where those tokens go and how SuperCompress gives the agent a tool that keeps only the lines that answer the task.
npm install -g supercompress-proxy && supercompress setup; setup finds Cline, Roo Code and Kilo Code in VS Code and adds the SuperCompress MCP server to each.
Where Cline tokens go
- Task history. Every earlier message and tool result in the task goes back with the next request.
- File reads. Whole files, often several per step.
- Terminal output. Full logs from tests, builds and installs.
- MCP servers and custom instructions. Added to every request.
Habits that cut Cline token usage for free
- Small tasks. Start a new task when the work changes.
- Ignore generated code. Use the ignore file (for example
.clineignore) for build output and vendored code. - Watch the context bar. When it fills up, start a new task with a short handoff note.
- Switch off unused MCP servers.
These habits shrink what goes in. They don't help when the agent genuinely needs to run a test suite or read a large file and only a few lines of the output matter. That is the part SuperCompress handles.
How SuperCompress works
SuperCompress is hosted, extractive and query-aware. Your agent sends a large block of context (a log, a diff, a file read, an MCP result) together with the question it is working on. Our Neural Keep model scores the lines against that question, keeps the original lines that answer it, and drops the rest. It never rewrites or summarizes, so file paths, error messages, IDs and code come back exactly as they were. The question itself is never compressed.
Every compress call reports original_tokens and kept_tokens, so you can see what was dropped on your own work instead of trusting a headline number. The usage_summary MCP tool shows totals per agent for your account.
What supercompress setup adds to Cline
| What | Where | What it does |
|---|---|---|
| MCP server | The extension's cline_mcp_settings.json in VS Code storage (Cline, Roo Code, Kilo Code) | Gives the agent the compress_context, connect_account and usage_summary tools. |
Ask the agent to run large logs, diffs and files through compress_context with the task as the query, or add that line to your custom instructions.
Install
npm install -g supercompress-proxy && supercompress setupSetup links your SuperCompress account in the browser, detects the coding agents on the machine and wires each one. Restart the agent so it loads the new MCP server. Then check what is wired up:
supercompress doctordoctor prints a per-agent health check. supercompress uninstall removes only the entries SuperCompress added. Setup backs up each config file before it edits it.
When to skip it
- Short sessions with small tool results. There is little to drop.
- Files the agent is about to edit line by line. It needs those in full.
- Work where every byte must be passed through unchanged for compliance reasons.
FAQ
Does SuperCompress change how I sign in to Cline?
No. You keep your normal Cline login and models. SuperCompress adds an MCP server and instructions to Cline; it does not route Cline's model traffic through a proxy.
Does SuperCompress summarize what Cline reads?
No. It is extractive. The lines it keeps are copied from the original output, so file paths, error messages and code stay exactly as they were.
How do I undo the Cline setup?
Run supercompress uninstall. It removes only the entries SuperCompress added, so your other MCP servers, hooks and instructions stay as they were.