How do I install the Tokeneconomics skill?

Run npx skillmds@latest add florianbuetow/tokeneconomics in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Tokeneconomics safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Tokeneconomics?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Tokeneconomics free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Tokeneconomics?

florianbuetow (@florianbuetow) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Tokeneconomics by florianbuetow — Agent Skill

Name: Tokeneconomics
Author: florianbuetow

Tokeneconomics

Analyze Claude Code session token usage to flag waste and optimization opportunities. Use when the user asks to "analyze token usage", "check token efficiency", "audit token spend", "tokeneconomics", "reduce token costs", "optimize token usage", "check my burn rate", or mentions token waste, session costs, usage limits, cache efficiency, or conversation sprawl.

florianbuetow Updated Sep 17, 2026

File contents

Token Economics — Usage Analysis & Optimization

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.

Workflow

Step 1: Determine scope

From the user's request, determine:

Project scope (default): analyze the current working directory's sessions
Global scope: if the user says "all projects", "everything", "all repos", or "overall"

Also determine the time window:

Default: 30 days
Override if the user specifies a different period (e.g., "last week" → 7, "last 3 months" → 90)

Step 2: Run the analysis

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>

Step 3: Present findings

Display the full report output inline. Do NOT hide it behind a file path.

After the report, highlight:

The single highest-impact action the user can take right now
Any critical (score 1) or poor (score 2) dimensions that need attention

Step 4: Offer deeper analysis

If the user wants to dig into a specific dimension or session, offer to:

Read the waste taxonomy reference: references/waste-taxonomy.md
Show the scoring benchmarks: references/benchmarks.md
Run with different time windows or project filters

Key Rules

Always show the report inline — never just save to a file
The report uses API pricing as a proxy; for subscription users, frame costs as "relative token burn" that affects usage limits, not actual billing
Do not editorialize beyond what the data shows — let the numbers speak
If no usage data is found, check that the project slug matches and suggest using --all to see all projects

---name: tokeneconomicsdescription: Analyze Claude Code session token usage to flag waste and optimization opportunities. Use when the user asks to "analyze token usage", "check token efficiency", "audit token spend", "tokeneconomics", "reduce token costs", "optimize token usage", "check my burn rate", or mentions token waste, session costs, usage limits, cache efficiency, or conversation sprawl.---# Token Economics — Usage Analysis & OptimizationAnalyze Claude Code session logs to measure token efficiency across sixdimensions: cost, cache efficiency, conversation sprawl, model selection,output efficiency, and session patterns. Produces a scored report withrisks, opportunities, and actionable recommendations.## Workflow### Step 1: Determine scopeFrom the user's request, determine:- **Project scope** (default): analyze the current working directory's sessions- **Global scope**: if the user says "all projects", "everything", "all repos", or "overall"Also determine the time window:- Default: 30 days- Override if the user specifies a different period (e.g., "last week" → 7, "last 3 months" → 90)### Step 2: Run the analysisRun the analysis script with the determined scope:**Project scope:**```bashpython3 "${CLAUDE_PLUGIN_ROOT}/scripts/tokeneconomics.py" --days <N>```**Global scope:**```bashpython3 "${CLAUDE_PLUGIN_ROOT}/scripts/tokeneconomics.py" --all --days <N>```### Step 3: Present findingsDisplay the full report output inline. Do NOT hide it behind a file path.After the report, highlight:1. The **single highest-impact action** the user can take right now2. Any **critical** (score 1) or **poor** (score 2) dimensions that need attention### Step 4: Offer deeper analysisIf the user wants to dig into a specific dimension or session, offer to:- Read the waste taxonomy reference: `references/waste-taxonomy.md`- Show the scoring benchmarks: `references/benchmarks.md`- Run with different time windows or project filters## Key Rules- Always show the report inline — never just save to a file- The report uses API pricing as a proxy; for subscription users, frame costs as "relative token burn" that affects usage limits, not actual billing- Do not editorialize beyond what the data shows — let the numbers speak- If no usage data is found, check that the project slug matches and suggest using `--all` to see all projects

Frequently asked questions