Charts of What You Spent Is Not a Score for What You Produced

The short version: ccflare

ccflare is a visual dashboard for Claude Code usage. It renders your token consumption as pretty charts — graphs, trends, heat maps of what you spent over time. It does the visualization layer well: clean, attractive, easy to read. But visualization is not evaluation. A chart of what you spent does not tell you if you are good at this.

SigRank takes the same token telemetry and asks a different question: how efficiently are you producing? 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. ccflare is the chart; SigRank is the score. Both matter. Only one tells you if you are winning.

Feature comparison

Why consumption charts aren't production scores

ccflare answers "what does my token consumption look like over time?" That is a visualization, not an evaluation. Two operators can have identical consumption charts and wildly different yields. One reuses cached context efficiently and produces 30K output tokens; the other re-sends the same context every turn and produces 3K. Same chart, ten-fold difference in signal. ccflare shows the same graph 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. ccflare gives you the chart; SigRank tells you whether the cascade it describes is compounding or burning.

From charts to scores

If you already run ccflare, you have the token telemetry. SigRank reads the same logs and adds the scoring layer visualizers 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 ccflare alternative?

They serve different purposes. ccflare is a visual dashboard for Claude Code usage — pretty charts of token consumption over time. It is excellent at visualization: you see your spending as graphs, trends, and heat maps. SigRank is a scoring layer: it takes the same token telemetry and computes cascade efficiency (Υ Yield), assigns a class tier, and ranks operators globally. ccflare visualizes what you spent; SigRank scores what you produced. Charts of consumption is not a score for production.

Why is visualizing consumption not the same as scoring production?

Consumption charts show you what you spent — input tokens, output tokens, cost over time. They are backward-looking accounting visualizations. A production score tells you how efficiently you converted that spend into signal. Two operators can have identical consumption charts and wildly different yields. One reuses cached context efficiently; the other re-sends it every turn. The charts look the same; the yield is ten-fold different. ccflare shows the chart; SigRank shows the score.

What does ccflare not measure that SigRank does?

ccflare visualizes token consumption as charts. 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). ccflare tells you what your spending looks like; SigRank tells you whether your cascade is compounding or burning. A chart is a visualization; a score is an evaluation.

Can I use both ccflare and SigRank?

Yes. ccflare is a visualization tool; SigRank is a scoring and ranking tool. Run ccflare for the consumption charts and trend visualizations. 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. Many operators use a visualizer for day-to-day awareness and SigRank for efficiency scoring and leaderboard submission.

Does ccflare work with tools other than Claude Code?

No. ccflare is a Claude Code usage dashboard — 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, ccflare is fine for consumption visualization. If you use multiple tools and want a comparable efficiency score across all of them, SigRank is the answer.