Claude Spend — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Claude Spend (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
See where your Claude Code tokens go. One command. Local dashboard. No setup.
npx @mpalermiti/claude-spendclaude-spend dashboard
Reads your local Claude Code session data (~/.claude/) and shows you exactly where your tokens go. Everything runs locally. Nothing leaves your machine.
Your Claude Code subscription hides how much API-equivalent value you're actually using. claude-spend reveals it. Select your plan ($100 or $200/mo), and the dashboard shows your multiplier — how many times over you're getting your money's worth.
26.7x value from your $200/mo plan
This is the stat that makes you feel good about your subscription. And the one your followers will screenshot.
| Feature | Original | v3 |
|---|---|---|
| Token usage chart | Basic bar chart | Stacked bars + 7-day moving average + cumulative cost line |
| Date filtering | None | 6 presets + custom range |
| Cost estimation | None | Full API-equivalent cost with per-model pricing |
| ROI multiplier | None | Plan-aware, shows Nx value vs subscription |
| Trend comparison | None | Cost/token delta vs previous equivalent period |
| Activity heatmap | None | Hour x day-of-week grid with peak callout |
| Session drill-down | None | Per-turn cost chart, context growth, token breakdown |
| Chart tooltips | None | Hover daily bars and donut for detailed breakdowns |
| Smart insights | None | 12 automated insights (vague prompts, marathon sessions, model waste) |
| Project breakdown | None | Per-project tokens with expandable prompt drawers |
| Tool usage | None | Top 15 tools, ranked color gradient |
| Share card | None | 1200x630 PNG with hero cost, ROI badge, stats |
| Keyboard navigation | None | j/k navigate, Enter drill down, / search, d dark mode |
| Dark mode | None | Full dark theme with CSS variable system |
| MCP server | None | 5 tools — Claude can query its own spend |
| Design | Basic HTML table | Emerald identity, Plus Jakarta Sans + JetBrains Mono, dot grid, micro-interactions |
npx @mpalermiti/claude-spendCLI flags:
--port <port> Custom port (default: 3456)
--no-open Don't auto-open browser
--mcp Run as MCP server (stdio)
--help Show help| Key | Action |
|---|---|
j / k | Navigate sessions |
Enter | Open drill-down |
Escape | Close drill-down / modals |
/ | Focus search |
d | Toggle dark mode |
r | Refresh data |
Add this to ~/.claude/settings.json and Claude can query spend data during any conversation:
{
"mcpServers": {
"claude-spend": {
"command": "npx",
"args": ["@mpalermiti/claude-spend", "--mcp"]
}
}
}Five tools: get_spend_summary, get_top_sessions, get_project_breakdown, get_insights, get_daily_trend. All accept optional from/to date params.
Claude Code writes JSONL session files to ~/.claude/projects/. This tool parses them, calculates API-equivalent costs per model (with cache write/read pricing), aggregates by day/model/project, and generates insights. The cost numbers represent what the usage would cost at API rates — not what you pay on a subscription. That gap is your ROI.
Forked from claude-spend by Aniket Parihar. I kept the core JSONL parser concept, then rebuilt everything else: the dashboard, date filtering, analytics engine, insights, drill-downs, heatmap, share card, keyboard nav, MCP server, and the design. MIT license.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.