I spent $514 on Claude Code in 30 days. Here's what I learned.

Real data from 50 sessions. The good, the bad, and the expensive.

The setup

For the past month, I've been tracking every Claude Code session with claudestat — an open-source tool I built to monitor token usage, costs, and patterns.

This isn't a hypothetical study. These are my real numbers from real work on real projects.

The numbers

30-day period: April 12, 2026 → May 10, 2026

That's about $18/day on average. For context: I'm on Max 5, so this isn't cheap.

The most expensive session

April 26, 2026 — I let Claude run on a refactoring project for hours without checking:

• Cost: $32.94
• Loops detected: 31
• Efficiency score: 35/100
• What happened: Claude went in circles editing files, each edit triggering more edits. I wasn't watching.

That's $33 in one session. More than my daily coffee budget for a month.

Key lesson: Loops are expensive. 31 loops × average tool call cost = $33 down the drain.

The project breakdown

Who consumed the most?

63% of my spending went to one side project. It's not my main job — it's my hobby project that's burning my quota.

This is the kind of insight you only get from tracking.

The loop problem

375 loops detected across 50 sessions.

That's ~7.5 loops per session on average. But it's skewed:

• 12 sessions had more than 10 loops
• 9 sessions had efficiency below 50%

Most loops look like:

Read → Edit → Edit → Edit → Read → Edit → Edit → Edit

Claude tries something, it doesn't work, tries slightly different, repeats. This is where most of my waste came from.

What I learned

1. Loops are the silent killer

I wasn't aware of loops until I saw the data. Now I watch for:

• Same tool called 3+ times in a row
• Context creeping up while output stays flat
• "Let me try..." messages from Claude

2. One project dominates

63% on claudetrace — I would have guessed 40/60 at best. Tracking revealed the truth.

3. Efficiency varies wildly

• Best session: 100/100 (perfect)
• Worst session: 35/100 (that $32.94 day)

Understanding this helps me spot when I'm about to have a bad session.

4. Bash is my most expensive tool

Running claudestat top shows Bash at 35-45% of total cost across all sessions. Batch your commands.

How to track your own data

npm install -g @statforge/claudestat
claudestat install
claudestat start
# ... use Claude Code normally ...
claudestat export json > my-data.json

Then analyze:

• Total spent → claudestat export | jq '.[].total_cost_usd | add'
• Top projects → claudestat export | jq 'group_by(.project_path) | map({project: .[0].project_path, cost: map(.total_cost_usd | add)})'
• Problem sessions → Look for efficiency < 50 or loops > 10

What's next

Now that I have this data:

1. I set up alerts at 70%, 85%, 95% quota → no more surprises
2. I use the kill switch at 95% → prevents runaway sessions
3. I check top tools weekly → batch those Bash commands
4. I watch for loops → stop them early

The black box is open. You have the data.

Try it

npm install -g @statforge/claudestat

Questions? Drop them in the comments.

Data from my actual sessions. Not estimated. Not hypothetical.