Rolling Context for Claude Code

A transparent proxy that gives Claude Code rolling context compression — old messages get automatically summarized while recent messages stay fully verbatim. You never hit the context wall, and you never lose important details.

Zero config. Uses your existing Claude Code auth. No API key needed. Just install and forget.

Claude Code's built-in /compact replaces your entire conversation with a lossy summary. After a few compactions, you're summarizing a summary of a summary. This plugin only compresses old messages — recent context stays untouched.

It's also a cost story: every token you carry in context gets re-billed on every turn (at cache-read rates), so an unmanaged session's input cost grows with the square of its length. Capping the prefix makes it linear — the math works in relative units and holds for every model, and it matters more the bigger the context window, not less.

/compact vs Rolling Context

	/compact (built-in)	Rolling Context
What gets compressed	Everything	Only old messages
Recent context	Summarized (lossy)	Kept verbatim
When it runs	Manual or near the context limit	Automatic, background
Latency impact	Blocks until done	Zero — async
After multiple compressions	Summary of summary of summary	Fresh rolling merge each time
Input cost over a long session	Grows with the square of session length	Grows linearly
Original transcript	Replaced	Preserved (JSONL unchanged)

The economics: why capping the prefix matters

No price cards needed — the argument works in relative units that hold for every Claude model. Take the model's fresh-input-token rate as 1×. The API bills:

Operation	Relative cost
Fresh input tokens	1×
Prompt-cache read	0.1×
Prompt-cache write	1.25× (5-min TTL) / 2× (1-hour TTL)
Output tokens	~5×

Claude Code re-sends the entire conversation on every turn. Even with caching working perfectly, each turn costs prefix size × 0.1. So a session's total input cost is the sum of the prefix over all turns:

• Unmanaged context (big window, auto-compact only near the limit): the prefix grows every turn, so total cost grows with the square of session length. A 1M window doesn't fix this — it just lets the prefix run to 900K+ before anything stops it, and every one of those tokens costs 0.1× again on every single turn.
• Rolling context: the prefix is capped between TARGET and TRIGGER, so total cost grows linearly.

The cache-miss blast radius matters even more in interactive use. The prompt cache has a TTL. Read a diff, think for a while, get coffee — and the next turn re-writes the whole prefix at 1.25×. At a 900K prefix, one cold turn bills the equivalent of ~1.1M fresh input tokens. With the prefix capped at ~100K, the identical cold turn is ~9× cheaper. Compression doesn't just shrink the average turn — it caps the worst one.