Is the Cost Tracker skill free?

Yes. The skill itself is free from rohitg00/pro-workflow. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Cost Tracker SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 3/5.

How do I install Cost Tracker?

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 Cost Tracker 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.

Cost Tracker

Static reference for what drives Claude Code session cost and per-task-type budget thresholds — not a transcript auditor.

by rohitg00 · rohitg00/pro-workflow

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.0/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 933d9fa

Gives concrete per-task-type dollar and tool-call budgets (e.g. bug fix: $0.10-0.50, 30-call budget, wrap up at 25) but doesn't compute your actual session cost itself — it just points you at Claude Code's own /cost output. (Listed here under our older name; the skill's own name is "Cost Tracker".)

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 7/10
Docs & honesty 3/5

What Cost Tracker does

Cost Tracker is a reference skill for session cost awareness: a cost-drivers table (large file reads, broad greps, subagent spawning, chatty tool loops), dollar and tool-call budgets by task type (bug fix vs. feature vs. refactor), and a fixed output template for reporting cost mid-session. It leans on Claude Code's own /cost output for the actual numbers rather than parsing transcripts or CLAUDE.md itself, so it's narrower than 'audit my transcript for bloat' — it's closer to 'tell me what typically burns tokens and what budget to set.'

How to install Cost Tracker

git clone https://github.com/rohitg00/pro-workflow
cd pro-workflow
mkdir -p ~/.claude/skills
cp -r skills/cost-tracker ~/.claude/skills/token-budget-auditor

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

Commands — how to trigger Cost Tracker

/token-budget-auditor Static reference for what drives Claude Code session cost and per-task-type budget thresholds — not a transcript auditor.

It also activates on plain-language prompts like these:

Audit this transcript for what's actually burning tokens
Find the bloated context in my CLAUDE.md setup
Check my skill setup for redundant file reads and chatty loops

Frequently asked questions

Is the Cost Tracker skill free?: Yes. The skill itself is free from rohitg00/pro-workflow. SkillProof publishes the install command and an independent test verdict at no cost.
Does Cost Tracker work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Gives concrete per-task-type dollar and tool-call budgets (e.g. bug fix: $0.10-0.50, 30-call budget, wrap up at 25) but doesn't compute your actual session cost itself — it just points you at Claude Code's own /cost output. (Listed here under our older name; the skill's own name is "Cost Tracker".)
What is the Cost Tracker SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 3/5.
How do I install Cost Tracker?: 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 Cost Tracker 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.