Check Your Agent Star on GitHub

Where does your Claude Code money actually go?

Source-available forensics and observability for AI coding-agent spend, behavior, and FinOps. Free for personal and internal use.

spend breakdown · my last 102 sessions $1,540 total
necessary spend$1,340
late compaction$123
oversized tool results$61.65
redundant re-reads$13.73
stale continuation$1.83
avoidable $200 — 13% of spend
bash 
$ uvx checkyouragent
# installs and opens the app at http://127.0.0.1:8000

what it finds

Spend mindmap showing habits and anti-patterns across Claude Code sessions
01 / 07 Habit & anti-pattern mindmap
Subgroup analysis of tool call errors — what combinations drive cost
02 / 07 Tool error subgroup analysis
Late compaction forensics — context window cost breakdown
03 / 07 Late compaction forensics
Detailed token spending across Claude Code sessions
04 / 07 Project & session cost
Detailed session events and turns
05 / 07 Session forensics
Turn cost and cost-outlier detection
06 / 07 Turn outlier analysis
Plan rate-limit hit analysis across recorded five-hour usage windows, by plan tier
07 / 07 Plan limit-hit analysis