Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From tokeneconomics
Analyzes Claude Code session token usage across cost, cache efficiency, sprawl, model selection, output, and patterns to score risks and recommend optimizations.
npx claudepluginhub florianbuetow/claude-code --plugin tokeneconomicsHow this skill is triggered — by the user, by Claude, or both
Slash command
/tokeneconomics:tokeneconomicsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analyze Claude Code session logs to measure token efficiency across six
Monitors and analyzes AI token consumption across providers, detects waste patterns (verbose output, low cache hit, high reasoning), estimates theoretical costs, and optimizes usage. Inspired by CodeBurn.
Tracks tokens, analyzes caching behavior, identifies bottlenecks in tool usage, and estimates costs to optimize Claude Code session performance and efficiency.
Routes Claude Code token usage and cost analysis requests to sub-skills for health checks, cost audits, anomaly detection, project reviews, trends, and usage patterns. Provides quick overviews for ambiguous intents.
Share bugs, ideas, or general feedback.
Analyze Claude Code session logs to measure token efficiency across six dimensions: cost, cache efficiency, conversation sprawl, model selection, output efficiency, and session patterns. Produces a scored report with risks, opportunities, and actionable recommendations.
From the user's request, determine:
Also determine the time window:
Run the analysis script with the determined scope:
Project scope:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/tokeneconomics.py" --days <N>
Global scope:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/tokeneconomics.py" --all --days <N>
Display the full report output inline. Do NOT hide it behind a file path.
After the report, highlight:
If the user wants to dig into a specific dimension or session, offer to:
references/waste-taxonomy.mdreferences/benchmarks.md--all to see all projects