The moment I realized something was wrong
I'd been using Claude Code every day for months.
Then one day I asked myself a simple question:
"How much have I actually spent?"
I had no idea.
Not approximately. Not roughly.
Zero visibility into what was happening.
That's when I understood the real problem.
It's not about cost. It's about trust.
AI agents are moving fast. Trust infrastructure isn't.
Claude Code can read files, write code, run commands,
and make decisions on your behalf.
But there's no dashboard. No audit trail.
No way to know what happened, why, or what it cost.
We're giving AI agents more and more autonomy
while building less and less visibility into their actions.
That's a problem that compounds.
What I'm building
I started with the most obvious gap:
token visibility for Claude Code users.
The data was always there — sitting in
~/.claude/projects/ as JSONL files.
Nobody told you it existed.
So I built a dashboard that reads it locally.
Nothing leaves your machine.
What I found in my own data:
- $266 spent since March
- One project eating 35% of my budget
- 95.9% cache read ratio — happening every turn, invisibly
But the dashboard is just the beginning
The real goal is bigger.
Think about how we built trust around cars:
- License (who's allowed to drive)
- Inspection (is it safe to operate)
- Insurance (who's responsible when something goes wrong)
AI agents need the same stack.
That's what I'm working toward:
- Identity — which AI did what
- Permissions — what it's allowed to do
- Audit trails — what actually happened
- Cost accountability — who pays for what
The dashboard is the audit trail layer.
AgentPass is the identity and permission layer.
Together, they're the foundation of
what I'm calling the AI trust infrastructure.
Why this matters now
We're at the moment right before the problem becomes obvious.
Most companies still say "ChatGPT is convenient."
But AI agents are already making decisions,
sending emails, placing orders.
The question isn't whether AI will act autonomously.
It's whether humans will be able to understand,
verify, and trust those actions.
I'm building the infrastructure for that trust.
What's new in v6
Since this article was published, the dashboard has grown significantly
based on feedback from real Claude Code builders.
What it shows now:
- Token usage by project
- Cost display adapted to your plan (Pro/Max: token volume · API: dollar cost)
- CLAUDE.md file sizes — re-sent every turn, most people don't realize this
- Cost reduction insights — which projects to optimize first
- Per-session drill-down — click any project to see individual sessions
Still local. Still private. Still free.
Try the dashboard
npm install -g @notenkidev/claude-token-dashboard
claude-token-dashboard
GitHub: https://github.com/notenkitoclient-cpu/claude-token-dashboard
If you're building in this space —
identity, permissions, audit, cost accountability for AI agents —
I'd love to connect.
Update — v0.1.17: the audit layer is now real
Since writing this, the vision has gotten more concrete.
Two new features shipped:
Activity Log — Claude Code's actions now stream into the dashboard
in real-time. Every file read, every command executed, every API call.
Risk-labeled. Timestamped. Live.
This is the audit trail I was describing. It's working.
Security Score — your Claude Code environment scored out of 100.
Permissions, denied paths, strictMode, hooks.
See exactly where your exposure is.
The trust layer isn't a concept anymore.
It's running on your machine right now.
npm install -g @notenkidev/claude-token-dashboard
claude-token-dashboard
Launching on Product Hunt June 9th.
Top comments (0)