Speed of Burning Is Not Quality of Operating

The short version: ccburn

ccburn is a Claude Code burn-rate tracker. It shows how fast you are burning tokens in real time — a live speedometer for token consumption. It does one thing well: it shows you how fast you are spending. That is useful for awareness — knowing when you are burning hot. But burn rate is a consumption velocity, not an efficiency metric. Burning fast does not mean burning well.

SigRank takes the same token telemetry and asks a different question: how efficiently are you compounding? 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. ccburn is the speedometer; SigRank is the lap time. Both matter. Only one tells you if you are winning.

Feature comparison

Why burn rate isn't yield rate

ccburn answers "how fast am I burning tokens?" That is a consumption velocity, not an efficiency metric. Two operators can burn tokens at the same rate 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 burn rate, ten-fold difference in signal. ccburn sees the same speed either way.

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. ccburn gives you the burn rate; SigRank tells you whether the cascade it describes is compounding or burning.

From burn rate to yield rate

If you already run ccburn, you have the token telemetry. SigRank reads the same logs and adds the scoring layer burn-rate monitors 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 ccburn alternative?

They measure different rates. ccburn shows your Claude Code burn rate in real time — how fast you are burning tokens right now. SigRank shows your yield rate: Υ = cache_read × output / input². Burn rate tells you how fast you are spending; yield rate tells you how efficiently you are compounding. Speed of burning is not quality of operating. You can run both — ccburn for the real-time burn dashboard, SigRank for the efficiency score and leaderboard.

Why is burn rate not the same as yield rate?

Burn rate measures how fast you consume tokens. Yield rate measures how efficiently you compound them. An operator burning tokens fast but re-sending the same context every turn has a high burn rate and a low yield. An operator burning tokens slowly but compounding cached context into high-yield output has a low burn rate and a high yield. Speed of burning is consumption velocity; yield is signal efficiency. The first tells you how fast you are spending; the second tells you whether the spending is worth it.

What does ccburn not measure that SigRank does?

ccburn reports tokens burned per unit time. SigRank derives the cascade architecture from the same four pillars: 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). ccburn tells you how fast you are burning; SigRank tells you whether your cascade is compounding or burning. Burn rate is a speedometer; yield is a lap time.

Can I use both ccburn and SigRank?

Yes. ccburn is a real-time burn-rate monitor; SigRank is a scoring and ranking tool. Run ccburn for the live burn-rate dashboard while you work. Run `sigrank submit` to get your Yield score, class tier, and leaderboard rank. They read from the same local session logs and do not conflict. ccburn is for real-time awareness; SigRank is for evaluation and competition.

Does ccburn work with tools other than Claude Code?

No. ccburn is a Claude Code burn-rate tracker — it reads Claude Code logs specifically. SigRank is platform-neutral: it works across Claude Code, Cursor, GitHub Copilot, ChatGPT, Gemini, and 15+ other platforms. If you only use Claude Code, ccburn is fine for real-time burn monitoring. If you use multiple tools and want a comparable efficiency score across all of them, SigRank is the answer.