Cchubber

CC Hubber

[](https://www.npmjs.com/package/cchubber) [](https://www.npmjs.com/package/cchubber)

Your Claude Code usage, diagnosed. One command.

npx cchubber

Reads your local data, generates an HTML report. No API keys, no accounts. Sends anonymous stats for community benchmarks ([details](#telemetry)). Opt out: `--no-telemetry`.

Built during the March 2026 cache crisis because nobody could tell if they'd been hit. Thousands of users burning through limits 10-20x faster than normal, and Anthropic's only answer was "we're investigating." We wanted receipts.

What you get

A single HTML report that tells you three things: what you spent, why you spent it, and whether that's normal.

**The diagnosis:**

• Cache health grade (trend-weighted, recent 7 days count more)
• Inflection point detection: "Your efficiency dropped 3.2x starting March 17"
• Per-project cost breakdown with decoded project names
• Session intelligence: duration stats, tool usage, activity heatmap
• Model routing analysis (93% Opus? Your limits would last 3x longer on Sonnet)
• 8 actionable recommendations, each with estimated usage savings

**The data:**

• Cost calculated from actual token counts (LiteLLM pricing, not the broken costUSD field)
• Message-level deduplication (Claude Code JSONL files contain ~50% duplicates from session resume)
• Subagent visibility: Haiku and Sonnet background agents show up in model distribution
• CLAUDE.md section-by-section analysis with per-message cost impact
• Cache break estimation even when diff files don't exist on your CC version

**The shareable card:** An animated card with your grade, spend, cache ratio, and diagnosis line. Export as video. Post it. Let people see the numbers Anthropic won't show them.

Install

npx cchubber

Or globally:

npm install -g cchubber