Cross-Tool Token Metrics, Not Editor Lock-in

The short version: Zed

Zed is an excellent high-performance code editor — built in Rust for speed, with Zed AI bringing assistant and agent features into the editor. It surfaces some AI usage within its own UI. That is useful when you live entirely inside Zed. The moment you also use Claude Code for agentic terminal work, Copilot for inline completion, or Cursor for refactoring, those metrics fragment: each tool reports its own numbers, in its own format, locked to its own surface. There is no unified score.

SigRank is the platform-neutral layer that fixes that. It reads token telemetry from Zed, Claude Code, Copilot, Cursor, and 15+ other tools, scores them all on the same cascade axis (Υ Yield), and gives you one rank that follows you across editors. You don't switch editors to use SigRank — you add it alongside whatever you already drive.

Feature comparison

The editor lock-in problem

Zed's metrics are real — but they are editor-scoped and editor-locked. The numbers live inside Zed, in Zed's format, visible only in Zed's UI. They do not export. They do not compare to anyone outside Zed. And they vanish the day you try a different tool.

Most operators do not live in one editor. A realistic week: Zed for fast AI-assisted editing, Claude Code for agentic terminal tasks, Copilot for inline completions, maybe a Cursor refactoring pass. Zed's metrics cover one slice of that week. Your actual efficiency is the union — and SigRank is the only layer that scores the union on a single axis.

Your score follows you, not the tool

SigRank's operator identity is tied to you, not to your editor. Enroll once, submit from any tool, and every signed snapshot feeds the same leaderboard rank. Switch from Zed to Claude Code to Copilot over a month and your Υ trajectory reflects your driving across all three — not three disconnected per-editor gauges. That is the difference between a metric and a reputation.

Frequently asked questions

Does SigRank replace Zed?

No — SigRank is not an editor. Zed is a high-performance code editor where you write code; SigRank is the scoring layer that measures how efficiently you drive any AI tool, including Zed AI. You keep using Zed (or Claude Code, or Cursor) and run the SigRank CLI alongside it. SigRank reads your token telemetry locally, computes your Υ Yield, and publishes a signed snapshot to the leaderboard. Your editor stays; your efficiency gets measured.

Does Zed have AI usage metrics?

Zed surfaces some AI usage within its own UI — how many tokens a request consumed, context window pressure. That is editor-scoped and editor-locked: the numbers live inside Zed and do not leave it. SigRank reads the same underlying token flow but computes the full cascade architecture (Υ Yield, compression ratio, SNR, Leverage, Velocity), assigns a class tier, and lets you compare against every other operator on the board — including ones who never touch Zed.

Why does platform neutrality matter?

Because most operators do not use one tool. You might use Zed for fast AI-assisted editing, Claude Code for agentic terminal tasks, and Copilot for inline completions. Zed's metrics cover only the Zed slice; your actual efficiency is the union across all of them. SigRank is platform-neutral — it reads telemetry from Zed, Claude Code, Copilot, Cursor, and 15+ others, scores them on the same cascade axis, and gives you one comparable rank. Your score follows you across tools, not the other way around.

Can I use SigRank with Zed specifically?

Yes. The SigRank CLI reads token telemetry from Zed's local logs the same way it reads Claude Code's (ccusage is bundled for Claude Code; additional readers cover other platforms). Run `sigrank enroll` to create your operator identity, then `sigrank submit` to score and publish. Your Zed sessions contribute to the same leaderboard rank as your Claude Code or Copilot sessions — unified, not siloed.

What is the difference between Zed AI and SigRank metrics?

Zed AI's metrics answer "how many tokens did this request use?" — a per-request, editor-local view. SigRank's metrics answer "how efficiently does this operator drive AI across all their tools?" — a cascade-level, cross-platform view. Zed tells you what you spent in one editor; SigRank tells you your Υ Yield (is signal compounding or burning?), your class tier, and your global rank among all operators regardless of editor. The first is a gauge; the second is a leaderboard.