Is the Claude Usage skill free?

Yes. The skill itself is free from tdimino/claude-code-minoan. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Claude Usage SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Claude Usage?

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 Claude Usage 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.

Claude Usage

Ground-truth Claude token/cost reports by parsing JSONL directly, catching what ccusage misses.

by tdimino · tdimino/claude-code-minoan

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · ef06b95

Re-derived its dedup-by-message-id method against my own real ~/.claude/projects JSONL data: a naive same-scope count overcounted output tokens by ~60% (13.8M vs 8.6M) purely from undeduplicated streaming chunks, and missed 263 subagent files outright — a concrete, reproducible demonstration of the exact failure mode the skill claims to fix.

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 8/10
Docs & honesty 4/5

What Claude Usage does

Parses Claude Code's session JSONL files directly — including subagent sidechains that ccusage ignores — to produce ground-truth token counts and cost estimates broken down by day, week, model, session, or project. Triggers on requests to check API spend, audit token usage, generate cost reports, or explain why ccusage numbers look wrong.

How to install Claude Usage

git clone https://github.com/tdimino/claude-code-minoan
cd claude-code-minoan
mkdir -p ~/.claude/skills
cp -r skills/core-development/claude-usage ~/.claude/skills/claude-usage

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

Commands — how to trigger Claude Usage

/claude-usage Ground-truth Claude token/cost reports by parsing JSONL directly, catching what ccusage misses.

It also activates on plain-language prompts like these:

How much did I spend on the Claude API this month?
Generate a weekly cost report broken down by project
ccusage seems way too low, check the real token numbers

Frequently asked questions

Is the Claude Usage skill free?: Yes. The skill itself is free from tdimino/claude-code-minoan. SkillProof publishes the install command and an independent test verdict at no cost.
Does Claude Usage work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Re-derived its dedup-by-message-id method against my own real ~/.claude/projects JSONL data: a naive same-scope count overcounted output tokens by ~60% (13.8M vs 8.6M) purely from undeduplicated streaming chunks, and missed 263 subagent files outright — a concrete, reproducible demonstration of the exact failure mode the skill claims to fix.
What is the Claude Usage SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Claude Usage?: 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 Claude Usage 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.