Skip to content

/tokenscope

Judgment-layer review of Claude Code token usage. Use when the user asks to audit token costs, review Claude Code spending, check context waste, or interpret a tokenscope report. Runs the tokenscope profiler, then interprets its findings with knowledge of the project's actual

shell
$ npx -y skills add AviVAvi/TokenScope --skill tokenscope --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/tokenscope
How auto-invocation works

Context preview

The summary Claude sees to decide when to auto-load this skill.

Judgment-layer review of Claude Code token usage. Use when the user asks to audit token costs, review Claude Code spending, check context waste, or interpret a tokenscope report. Runs the tokenscope profiler, then interprets its findings with knowledge of the project's actual
Ships withtokenscope

A token profiler for Claude Code. It parses the session transcripts Claude Code already writes to disk (~/.claude/projects/**/*.jsonl) and tells you where your tokens actually went — and what to change to spend fewer of them. ccusage tells you what you spent.

Get the whole plugin, auto-invoked
Stats
6
Stars
0
Views
1
Forks
Active
Maintenance
TypeScript
Language
MIT
License
12d ago
Last commit
12d ago
Created

Repo: AviVAvi/TokenScope