Published Throughline to npm: A hook to offload Claude Code tool I/O to SQLite

A developer has published Throughline, a hook plugin for Claude Code that offloads tool I/O to SQLite to reduce token consumption. In a 50-turn session, the plugin reduced context from 125,000 tokens to within 13,000 tokens by removing tool I/O data and compressing older conversation turns to one-fifth their original size. Throughline also includes a multi-session token monitor that reads actual API values from transcript JSONL for accurate usage tracking.

I have published a hook plugin for Claude Code called Throughline https://github.com/kitepon-rgb/Throughline to npm. In a Claude Code session, the majority of the context is filled with the remnants of "tool I/O." The contents of read files, grep results, and Bash output—data that served its purpose the moment the AI read it, made a decision, and moved on. However, it stays in the context until the end, consuming tokens. Throughline manages the conversation in three layers. | Layer | Content | Context Injection | |---|---|---| | L2 | Conversation body user input + AI response | Last 20 turns injected as is | | L1 | Summarized version of L2 1/5th size while retaining key points | Injected for turns older than 20 | | L3 | Tool I/O, system messages, and thinking | Not injected; offloaded to SQLite, retrieved by Claude as needed | Since tool I/O is completely removed from the context, read grep results and Bash outputs do not linger until the end of the session. Older conversations are compressed to 1/5th of their original size while keeping key points, so you can still follow the context of decisions made dozens of turns ago. In a 50-turn session on my machine, a conversation that consumed 125,000 tokens was reduced to within 13,000 tokens. npm install -g throughline throughline install install registers the hook in ~/.claude/settings.json . It runs automatically for all Claude Code projects on your PC. No configuration is required for individual projects. Throughline offloads conversations to SQLite, so the data remains even after running /clear . If you want to carry over your memory to the next session, type /tl in the previous session. Data is only carried over to the next session when you type /tl . If you don't type it, it starts as a fresh session. Even if you open parallel windows or restart VSCode, it is designed so that it "won't fire accidentally unless you type /tl ." When carrying over, the "next step memo" written by the previous Claude and the internal reasoning thinking of the final turn are passed along as well. The next Claude runs in "continue from interruption" mode rather than "reading past logs" mode. As a byproduct, a multi-session capable token monitor is included. throughline monitor Throughline 1 session ▶ Throughline 2ed5039c ████░░░░░░░░░░░░░░░░ 205.1k / 21% Remaining 794.9k claude-opus-4-6 Since it reads actual API values message.usage from the transcript JSONL, it provides accurate values rather than estimates based on character count / 4 . It also supports automatic detection of 1M context windows. node:sqlite module Zero. The tarball published to npm contains only .mjs files. No build process or native bindings are required. The background of the design and my trial-and-error process are written in this article https://dev.to/quolu/why-i-gave-up-on-automatic-detection-for-resuming-sessions-in-claude-code-3bj0 . MIT licensed. Bug reports and PRs are welcome.