Spend Is the Input. Yield Is the Output.

The short version: lineman

lineman is a Claude Code spend tracker. It reads your token logs and shows how much you're spending — dollars burned, cost per session, spend over time. It does its job well: it accounts for the spend. But spend is the input, not the output. Two operators can spend the same $50 and get wildly different results. lineman can't tell them apart.

SigRank reads the same token telemetry and asks a different question: is the cascade compounding or burning? The headline metric, Υ Yield = cache_read × output / input², rewards the operator who reuses cached context efficiently and penalizes the one who burns fresh input without leverage. lineman counts the cost; SigRank measures the yield. Both matter. Only one tells you whether you're winning.

Feature comparison

Why spend tracking isn't yield scoring

lineman answers "how much did I spend?" That's accounting, not evaluation. Two operators can spend the same $50 and get wildly different outcomes. One reuses cached context efficiently and produces 30K output tokens; the other re-sends the same context every turn and produces 3K. Same spend, ten-fold difference in signal. On a spend tracker, they look identical. On a yield leaderboard, the gap is obvious.

SigRank's headline metric, Υ = cache_read × output / input², measures exactly that gap. It rewards the operator who compounds cached context into output and penalizes the one who burns fresh input without leverage. lineman gives you the bill; SigRank tells you whether the cascade it funded is compounding or burning.

From spend to yield

If you already run lineman, you have the token counts. SigRank reads the same telemetry and adds the scoring layer spend tracking never had:

npm install -g sigrank
sigrank enroll      # create your operator identity
sigrank submit      # reads logs, scores, signs, publishes

Prefer to inspect before you submit? Run sigrank me --dry-run to see your scored payload locally, or paste your token counts into the /score calculator to compute your Υ Yield, class tier, and compression ratio instantly, no account, no submission, just the numbers.

Frequently asked questions

Is SigRank a lineman alternative?

They overlap on reading Claude Code telemetry but diverge on what they do with it. lineman tracks spend — how many dollars you've burned on Claude Code. SigRank scores yield — how efficiently you're converting those dollars into signal. If you want a spend dashboard, lineman is that. If you want to know whether your spend is producing efficient output, SigRank answers that. You can run both — they read the same logs.

Why is spend tracking not enough?

Spend tracking tells you what you paid, not what you got. Two operators can spend the same $50 and get wildly different outcomes. One reuses cached context efficiently and produces 30K output tokens; the other re-sends the same context every turn and produces 3K. Same spend, ten-fold difference in signal. On a spend tracker, they look identical. On a yield leaderboard, the gap is obvious. Spend is the input; yield is the output.

What does lineman not measure that SigRank does?

lineman reports dollars spent on Claude Code. SigRank reads the same token telemetry and derives the cascade architecture: Υ Yield (is signal compounding or burning?), compression ratio (output per input), SNR (signal density), Leverage (how much cached context amplifies your input), and Velocity (tokens per unit time). lineman tells you what you paid; SigRank tells you whether the cascade it funded is compounding or burning.

Can I use both lineman and SigRank?

Yes. lineman gives you the spend dashboard for budget tracking. SigRank gives you the efficiency layer that spend tracking cannot provide. Run `sigrank submit` to publish your cascade score to the SigRank leaderboard, and keep lineman for the budget view. The two are complementary, not mutually exclusive. The same local logs feed both.

Which is better for improving my AI coding efficiency?

SigRank. Spend tracking can tell you when you're burning too much, but it can't tell you why. Yield tracks the root cause: an operator whose Υ is low is burning fresh input without compounding cached context. Fix the cascade and the spend drops automatically. lineman shows the symptom; SigRank shows the disease.