Works with the AI Agents you already use
Claude Usage Report
See real Claude Code token usage, cache hit rate and API-equivalent cost by day, model, project or session, from your local logs.
Free
claude-usage-report
Example session with this skill installed
How much did Claude Code cost me in the last 7 days and which project uses the most?
- Read your context and instructions
- Compiled the claude-usage-report
Claude Code usage since 2026-10-17: 1.4M tokens, ~$0.73 API-equivalent (19 requests). Cache hit rate: 97%. Top project: home/user.
Connects securely to your tools. The creator never sees your data.
About this skill
Read the JSONL session logs Claude Code already writes locally and turn them into a usage and cost report. The numbers are the real usage values returned by the API, not guesses. 100% local: no network, no prompt content is read out or printed, only token counts and metadata.
- "How many tokens / how much money did I use today / this week / this month?"
- "Which project or session burns the most tokens?"
- "Is my cache working?" (cache read vs. fresh input)
- The user wants to reduce spend and needs to know where it goes first.
Python 3, standard library only:
- Default root:
~/.claude/projects(use--rootfor another location). --days Nlimits to the last N days (default 30).--since YYYY-MM-DDoverrides it.--bychooses the breakdown (default: shows day, model and project tables).--pricesloads your own per-1M-token rates (see below).--jsonprints machine-readable output.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.
Cost is an API-equivalent estimate from an indicative price table, not your actual bill (Pro/Max plans are flat-rate). Models missing from the table use a fallback rate, marked with ~. Override with --prices.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 23 days ago
- Free with an Agensi account
- Software
Python 3Claude Code
Reads Claude Code session logs in ~/.claude/projects.
Permissions
File Scopes
Fully local. Reads only numeric usage fields, timestamps, model, session id and project folder name. Never prints message text. No network, no writes.