SIGNALAF
◈ SigRank vs Sourcegraph Cody

Operator Scoring, Not Codebase Context

Sourcegraph Cody brings codebase context to AI. SigRank is platform-neutral — scores how efficiently you drive Cody, Claude Code, Copilot, Cursor, and 15+ others. Your score follows you across tools.

The short version: Sourcegraph Cody

No, SigRank does not replace Sourcegraph Cody. Cody is a code-aware AI assistant — it indexes your entire codebase and brings that context to AI-generated answers and completions. That is a tool, not a metric. Cody surfaces some token and context information inside its extension, but it does not compute cascade efficiency, does not assign a class tier, and does not rank you against operators who use other tools. It brings context to AI; it does not measure how efficiently you drive AI.

SigRank is the platform-neutral layer that fixes that. It reads token telemetry from Cody, 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 tools. You don't switch assistants to use SigRank — you add it alongside whatever you already drive.

Feature comparison

FeatureCodySigRank
What it isCode-aware AI assistant (codebase context)Platform-neutral operator scoring layer
Token usage trackingLimited (extension-scoped)Yes (cascade-derived)
Cascade efficiency score (Υ = cache_read × output / input²)NoYes
SNR + Leverage + VelocityNoYes
Class tier (IGNITER to ARCH+)NoYes
Global operator leaderboardNoYes
Works across Cody + Claude Code + Cursor + 15+No (Cody only)Yes
Score follows you across toolsNoYes
Operator profiles + head-to-head compareNoYes
ed25519-signed snapshot submissionNoYes
MCP server for agent integrationNoYes
Privacy-preserving (token counts only)YesYes

Context is not measurement

Cody's job is to understand your entire codebase and bring that context to AI-generated answers. It does that well. But codebase context is a feature, not a metric. Cody surfaces some token and context information inside its extension UI, but those numbers are extension-scoped and extension-locked — they live inside Cody and do not leave it. The moment you want to know how efficiently you are driving AI — not just how much context was pulled in — Cody has nothing to say.

Most operators do not use one tool. A realistic week: Cody for codebase-aware questions, Claude Code for agentic multi-file tasks, Cursor for refactoring, maybe a Copilot inline completion. Cody covers only the codebase-context slice. Your actual efficiency is the union — and SigRank is the only layer that scores the union on a single axis.

The cascade is tool-agnostic

Υ = cache_read × output / input² is computed from four token integers that every AI tool produces — input, output, cache-read, cache-write. The math does not care which assistant generated them. An operator who reuses context efficiently in Cody scores the same way as one who does it in Claude Code. The cascade is the universal substrate.

Your score follows you, not the tool

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

Frequently asked questions

Does SigRank replace Sourcegraph Cody?
No. Sourcegraph Cody is a separate coding tool; SigRank measures token efficiency from supported sources. The current SigRank CLI has no dedicated Sourcegraph Cody log adapter, so merely installing SigRank does not import Sourcegraph Cody sessions or publish them to the leaderboard.
Does Cody have token usage metrics?
Usage or cost figures displayed by Sourcegraph Cody belong to that tool's own interface. SigRank does not automatically read Sourcegraph Cody logs; it measures supported local adapters and can separately calculate metrics from supplied four-pillar token counts. A manual calculation alone is not a verified leaderboard submission.
Why does platform neutrality matter?
Using multiple AI tools makes cross-tool comparison valuable, but input coverage matters. SigRank can aggregate two or more supported active sources when explicitly invoked with `npx sigrank submit --platform multi`; it does not automatically include Sourcegraph Cody. The default `npx sigrank submit` uses Claude telemetry.
Can I use SigRank with Cody specifically?
You can use Sourcegraph Cody alongside SigRank, but there is no dedicated Sourcegraph Cody log adapter at present. To publish from a supported local source, first create a connect code under SignalAF Settings, run `npx sigrank enroll`, preview with `npx sigrank submit --dry-run`, and then submit. The bare submit command uses Claude; other supported sources require an explicit --platform selection.
What is the difference between Cody and SigRank metrics?
Cody's metrics answer "how much codebase context did this request pull in?" — a per-request, extension-local view. SigRank's metrics answer "how efficiently does this operator drive AI across all their tools?" — a cascade-level, cross-platform view. Cody tells you what context you used in one assistant; SigRank tells you your Υ Yield (is signal compounding or burning?), your class tier, and your global rank among all operators regardless of assistant. The first is a gauge; the second is a leaderboard.

Keep Cody. Add the score that follows you.

SigRank can measure supported local token sources while you keep using Sourcegraph Cody. It has no dedicated Sourcegraph Cody log reader at present. To compare, use SigRank's manual calculator for supplied counts or enroll to submit signed telemetry from a supported platform.

Related: AI Coding Efficiency Tools · Measure AI Coding Efficiency · SigRank vs Cursor