Claude Token Analyzer
Your Claude Code sessions might be burning tokens you can't see. Diagnoses where your tokens go, why they're wasted, and what to fix first.
Fully local — parses your ~/.claude JSONL files into SQLite. Nothing leaves your machine. No cloud. No telemetry.
Features
- Diagnose token waste — Detects 6 statistical anomaly types (HighCost, LowCacheHitRate, CostInefficient, ExcessiveToolUse, HighTokenUsage, UnusualModelMix) with severity scoring
- Audit costs — Per-session, per-project, and global cost breakdowns with monthly trends
- Forecast spending — Daily/weekly/monthly usage trends with burn-rate projections
- Optimize cache — Identifies sessions with poor cache hit rates that inflate costs
- Prioritize fixes — Severity-scored anomalies so you know what to fix first, not just what's wrong
- Converse naturally — Ask in plain language: "how much did I spend?" or "scan for anomalies"
Quick Start
# Install (binary auto-downloads, no Rust toolchain needed)
claude plugin install claude-token-analyzer
Then just ask in any Claude Code session:
> cta
> how much did I spend this month?
> scan for anomalies
> analyze this project
> show me usage trends
How It Works
~/.claude/projects/**/*.jsonl Your session logs (never modified)
→ parser.rs Extract + deduplicate responses
→ analyzer.rs Cost calculation, 10-dimension metrics
→ storage.rs Upsert into local SQLite
→ detector.rs 6-type anomaly detection + severity scoring
→ MCP tools / Skills You ask, it answers
All processing happens locally. The SQLite database lives in the plugin directory. No network calls, no external dependencies at runtime.
Skills
| Skill | Trigger Phrases | What It Does |
|---|---|---|
cta | "cta", "analyze tokens" | Routes to the right sub-skill |
cta-health-check | "quick check", "overview", "看看狀況" | One-page usage summary |
cta-cost-audit | "monthly costs", "cost report", "這個月花多少" | Monthly cost breakdown with model split |
cta-anomaly-hunt | "anomalies", "problems", "有異常嗎" | Statistical anomaly scan with drill-down |
cta-project-review | "analyze project", "專案健檢" | Four-dimension project analysis |
cta-trend-watch | "trends", "burn rate", "趨勢" | Usage trend analysis with forecasting |
MCP Tools
| Tool | Purpose |
|---|---|
sync_db | Sync JSONL session logs to SQLite |
analyze_session | 10-dimension session analysis |
analyze_project | Project-level aggregation with sorting |
analyze_global | Cross-project panoramic view |
cost_report | Monthly cost report (daily granularity available) |
anomaly_scan | 6-type anomaly detection with severity scoring |
trend_report | Time-series trends (daily/weekly/monthly) |
Configuration
Environment variables (all optional):
| Variable | Purpose | Default |
|---|---|---|
CTA_DB_PATH | SQLite database location | ${CLAUDE_PLUGIN_ROOT}/data/token-analyzer.db |
CTA_PROJECTS_DIR | Session logs directory | ~/.claude/projects |
CTA_ARCHIVE_DIR | Archive directory | ~/.claude/token-analyzer-archive |
CTA_PRICING_PATH | Custom pricing TOML | Embedded in binary |
Path resolution priority: Environment variable > Plugin mode ($CLAUDE_PLUGIN_ROOT) > Standalone mode ($HOME/.claude/)
Building from Source
git clone https://github.com/li195111/claude-token-analyzer.git
cd claude-token-analyzer
bash scripts/build.sh
# Binary: mcp-server/target/release/cta-mcp-server
# Run tests (98 tests)
cargo test --all-targets --manifest-path mcp-server/Cargo.toml
# Lint
cargo clippy --manifest-path mcp-server/Cargo.toml -- -D warnings
# Launch with plugin loaded
claude --plugin-dir .
Requires: Rust toolchain
Contributing
Issues and PRs welcome! See open issues for starter tasks.
Development setup:
- Clone the repo and run
bash scripts/build.sh - Run
cargo test --all-targets --manifest-path mcp-server/Cargo.tomlto verify - Load the plugin locally with
claude --plugin-dir .
Rust toolchain required. The project uses cargo clippy -- -D warnings for linting.
License
MIT
繁體中文
你的 Claude Code 會話可能正在浪費你看不見的 token。 診斷 token 流向、浪費原因，並告訴你該優先修正什麼。
全本地運行 — 解析 ~/.claude JSONL 檔案到 SQLite。資料不離開你的機器。無雲端、無遙測。