Loading rankings…
Loading rankings…
Token counting vs cascade scoring
| Feature | SigRank | claudecount |
|---|---|---|
| What it measures | Cascade yield (Υ = cache_read × output / input²) | Claude Code token counts |
| What it tells you | How efficiently you compound signal | How many tokens you burned |
| Leaderboard | Yes — ranked by Yield, class tiers | No |
| Platform coverage | Claude Code, Cursor, Copilot, Gemini, 15+ | Limited |
| MCP server | Yes | No |
| Privacy | Token counts only — never prompt content | Token counts only |
claudecount counts Claude Code tokens. SigRank scores cascades. Counting is not scoring.
SigRank's Yield (Υ) metric measures the architecture of your token cascade — is signal compounding, or are tokens burned? That's the question claudecount can't answer.
claudecount counts Claude Code tokens. SigRank scores cascades. Counting is not scoring. SigRank's Yield (Υ) = (cache_read × output) / input² measures cascade efficiency.
Yes. They're complementary. Use claudecount for its function, and run sigrank submit to publish your cascade score to the leaderboard.
Yield (Υ) = (cache_read × output) / input² — token-cascade efficiency from real sessions. Works across Claude, GPT, Gemini, Cursor, Copilot, and any AI coding tool.
Visit signalaf.com/score to enroll and submit your token telemetry. SigRank will compute your Yield, your rank, and your operator class. Token counts only — never prompt content, never code.
Stop counting. Start scoring.
Check my Yield