Sipcode is a tool for Claude Code, which lives on your desktop. This site is built for the same screen.
Open this page on your laptop or desktop for the full experience.
Keep Claude Code's context clean for sharper answers and lower cost, automatically.
measured from your transcripts, not a brochure number.
Same task, same model. Watch what bloated context does.
Add a sign-out button to the navbar.
Adding a SignOutButton to src/NavBar.tsx, wired to the existing useSession() hook. Diff below.
Add a sign-out button to the navbar.
There are a few places this could live. Earlier you mentioned a sidebar, but the project also has a top nav. Should I add it to both? I also want to double-check the session hook still exists.
sharper outcomes when context stays lean. About 40% fewer agent errors under the same conditions.
Cited from published research. Not measured by Sipcode.
Answer quality drops measurably as input tokens climb. Even on tasks the same model aced at small context sizes.
A hook rewrites bulky commands to their compact form before Claude ever sees them.
sipcode proxy --install automatic · zero config Reads your local Claude transcripts. Tells you where tokens went and what you saved.
sipcode why · impact · stats 15 MCP tools · zero network calls Silent unless your latest session drifts off your baseline. Names what moved and how to fix it.
sipcode drift silent unless it matters npx sipcode benchmark What this means: your newest session is behaving differently from your recent norm, in ways that waste tokens and can make Claude less reliable.
(This is "context rot": answer quality drops as context gets bloated.)
Signals that regressed (2):
Each step is sending far more context than your norm. Bloated context costs more tokens and can bury the detail Claude needs.
→ Fix: Start a fresh chat for your next task to reset the context.
Much less of your context is being reused from cache (about 10x cheaper).
→ Fix: Avoid changing MCP servers or config mid-task.
Install the package, then turn on the proxy hook.
$ npm install -g sipcode
$ sipcode proxy --installRestart Claude Code. You are done.
Add the MCP server to your config, then restart Desktop.
{
"mcpServers": {
"sipcode": { "command": "npx", "args": ["-y", "sipcode-mcp"] }
}
}After restart, ask Claude "what sipcode tools do you have?" to confirm.
The npm route is what we ship. No curl | sh, no one-click installer that does nothing.
The Desktop pipeline is closed. The proxy only works in Claude Code. Desktop gets the analytics tools.
npm install -g sipcode puts the package on your machine. Tokens drop after you run sipcode proxy --install.
The 29% and 40% reliability numbers come from published research, cited not measured. We measure the tokens we save.
No telemetry. No network calls in any core path. A CI guard fails the build if that ever changes.
An open-source toolkit that keeps Claude Code's context clean. It rewrites bulky tool calls before they run (the proxy), measures what got saved (the meter), and warns you when a session starts to drift from your baseline (the drift detector). Newer features layered on top: re-read dedup that refuses to reload files Claude already has, integrity scoring that tells you how much signal a rewrite kept, and AST-aware reads that return only the symbol Claude searched for. MIT licensed.
Yes. Sipcode ships 15 MCP tools. Ask "how am I doing today?" and Claude routes to get_today_summary — spend so far plus comparison against your adaptive 30/14/7/3 day median. Ask "how much will I spend this month?" and it routes to forecast_monthly_spend — projected month-end with a confidence band. No SDK, no account, no telemetry; Sipcode reads the local .jsonl files Claude Code already writes.
Sipcode covers terminal use through Claude Code and chat use through Claude Desktop via 15 MCP tools. RTK is terminal only. Beyond coverage, Sipcode adds reliability infrastructure RTK does not have: a drift detector that catches context rot live, re-read dedup that refuses to reload files already in context, integrity scoring that tells you how much signal a rewrite kept, and AST-aware reads that return only the symbol the model searched for. You can use both. They do not conflict.
The reproducible benchmark shows a 62.6 percent median. Your number will depend on your workload. After install, sipcode proxy --stats shows the exact tokens rewritten on your machine.
Research shows leaner context lifts agent reliability. We cite that research. Sipcode measures the tokens it saves, not the quality lift, so we do not put a number on the quality side. You will judge for yourself.
Yes. MIT licensed. No account. No telemetry. No paid tier.
A gulp is a context dumped into Claude without restraint. It costs more and makes the model worse. A sip is the same information, measured. Sipcode keeps the intake at a sip.
Runs locally. No account. No telemetry. About 60 seconds to set up.