Is the Token Doctor skill free?

Yes. The skill itself is free from techwolf-ai/ai-first-toolkit. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Token Doctor SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.

How do I install Token Doctor?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Token Doctor with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Token Doctor

Reads your local Claude Code/Cowork transcripts and prints a real cost-shape diagnosis in the terminal.

by techwolf-ai · techwolf-ai/ai-first-toolkit

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 18, 2026 · 7d49104

Actually ran the two deterministic scripts against real local Claude transcripts on this machine and got genuine numbers back: $72.01 across 3 conversations, 77% of spend in one marathon session, $5.80 in cache-rebuild cost.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 4/5

What Token Doctor does

Scans local Claude Code and Cowork transcripts (and Codex rollouts, where present) to compute conversation-length distribution, marathon/zombie session share, cache-rebuild cost, and re-read ratio, then writes a doctor-report-style diagnosis directly in the terminal within seconds. An opt-in second stage fans out parallel Haiku subagents over the costliest and most efficient sessions and writes a per-session Markdown report. Triggers on questions about Claude/Cowork spend, token burn, or usage habits; explicitly not for task-inventory ('what have I worked on') or session-recall ('where did I do X') queries, which route to sibling skills.

How to install Token Doctor

git clone https://github.com/techwolf-ai/ai-first-toolkit
cd ai-first-toolkit
mkdir -p ~/.claude/skills
cp -r plugins/ai-adoption/skills/token-doctor ~/.claude/skills/token-doctor

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Token Doctor

/token-doctor Reads your local Claude Code/Cowork transcripts and prints a real cost-shape diagnosis in the terminal.

It also activates on plain-language prompts like these:

How much am I spending on Claude Code tokens and where's it going
Diagnose my Cowork transcripts for zombie sessions and cache waste
Give me a cost-shape report on my recent Claude usage habits

Frequently asked questions

Is the Token Doctor skill free?: Yes. The skill itself is free from techwolf-ai/ai-first-toolkit. SkillProof publishes the install command and an independent test verdict at no cost.
Does Token Doctor work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. Actually ran the two deterministic scripts against real local Claude transcripts on this machine and got genuine numbers back: $72.01 across 3 conversations, 77% of spend in one marathon session, $5.80 in cache-rebuild cost.
What is the Token Doctor SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.
How do I install Token Doctor?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Token Doctor with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.