claude-usage SKILL.md skillA
claude-usage from tdimino/claude-code-minoan is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tdimino/claude-code-minoan/claude-usage@git:20260221.bc87150Pins git:20260221.bc87150 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tdimino/claude-code-minoan
- Path
skills/core-development/claude-usage/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260221.bc87150, committed Feb 21, 2026
- First version recorded
- Feb 21, 2026
- Size
- 7,295 bytes
- Repository stars
- 41
- License
- MIT
Report ground-truth Claude token consumption and estimated cost by parsing JSONL session files directly. Use when checking API spend, auditing token usage by project/session/model, generating daily/weekly/monthly cost reports, or diagnosing ccusage undercounting. Includes subagent files that ccusage ignores.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Claude Usage
Ground-truth token usage and cost reporting for Claude Code sessions. Parses JSONL files directly—parent sessions and subagent sidechains—to produce accurate numbers.
## Why This Exists
ccusage (v18+, the standard community tool with 10.6k stars) **undercounts output tokens by 77-94%** for heavy users:
| Source | Output Tokens | Notes |
|--------|-------------|-------|
| Raw JSONL (all files) | 1,076,691 | Ground truth |
| Raw JSONL (date-filtered) | 412,987 | Properly filtered |
| ccusage --timezone UTC | 93,960 | 77% undercount |
| ccusage default | 62,375 | 94% undercount |
Three compounding bugs:
1. **Ignores subagent files** at `{session-uuid}/subagents/{agent-id}.jsonl`—132 files missed on a typical day with Agent Teams
2. **Timezone confusion** between UTC entry timestamps and local time filtering
3. **Drops entries** in parent files—even at UTC, reports only 23% of actual tokens
This script reads every JSONL file to produce correct totals.
---
## Usage
```bash
# Today's usage (default)
python3 ~/.claude/skills/claude-usage/scripts/claude_usage.py
# Last 7 days, broken down by day
…Read the whole file at its exact version.
How to install
mdr add tdimino/claude-code-minoan/claude-usage@sha256:3ce7b1fff0d4e90cThe line at the top of this page pins the label git:20260221.bc87150, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_up7ydywoghd3cko2)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, all committed on Feb 21, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260221.bc87150 latest | 2026-02-21 | bc87150 | 7,295 B | A | view · diff |
| git:20260221.32afdf8 | 2026-02-21 | 32afdf8 | 6,071 B | A | view · diff |
| git:20260221.b23fd4b | 2026-02-21 | b23fd4b | 5,817 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7295 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
tdimino/claude-code-minoan · 41 stars · license MIT · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_up7ydywoghd3cko2 GET https://markdownregistry.com/api/v1/resolve?ref=tdimino/claude-code-minoan/claude-usage GET https://markdownregistry.com/api/v1/blob/3ce7b1fff0d4e90c43f0d9de1ffc74e318aed509c4e2c6753f310476538773ac
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.