claude-usage-analyst
GitHub基于本地ccusage数据，分析Claude Code和Desktop的Token用量、成本及配额消耗。用于解释额度耗尽原因、模型费用对比及使用明细，提供面向非技术用户的清晰解读。
Trigger Scenarios
Install
npx skills add daymade/claude-code-skills --skill claude-usage-analyst -g -y
SKILL.md
Frontmatter
{
"name": "claude-usage-analyst",
"description": "Analyze Claude Code and Claude Desktop Code token usage, cost, quota burn, model mix, cache read\/write, and 5-hour block consumption using ccusage evidence. Use when the user asks why Claude quota was exhausted, whether a model such as fable\/opus\/sonnet is unusually expensive, how many tokens were spent today or historically, or needs a human-friendly explanation of local Claude Code CLI\/Desktop usage.",
"disable-model-invocation": true
}
Claude Usage Analyst
Overview
Use this skill to produce evidence-based usage explanations from local ccusage data. Separate observed numbers from interpretation, and explain quota burn in human terms.
Workflow
-
Verify
ccusageis available:ccusage --versionIf missing, install or update with
npm install -g ccusage@latestor run withnpx ccusage@latest. -
Run the bundled analyzer for the requested window:
python3 /path/to/claude-usage-analyst/scripts/analyze_claude_usage.py \ --since YYYY-MM-DD --until YYYY-MM-DD --timezone Asia/ShanghaiDefault
--since/--untilis today in the selected timezone. For historical comparison, set--sinceto an earlier date such as the first day of the month; otherwise rank/median fields only describe the single target day. -
If the user asks about a specific model comparison, pass aliases:
python3 scripts/analyze_claude_usage.py --model-a fable --model-b opus-4-8 -
Read
references/explanation-guide.mdwhen writing the final answer.
Evidence Rules
- Base numeric claims on
ccusageoutput or the bundled analyzer output. - State the scope:
ccusage claudemeasures local Claude Code usage logs, including Claude Desktop's Claude Code sessions when those local logs exist. It is not a complete ordinary Claude.ai chat bill. - Report dates with timezone.
- Explain cache clearly: cache read tokens are still usage/quota pressure even though the user did not type those words.
- Do not infer Anthropic plan quota rules from local token counts unless the user provides plan details. Say "quota-like pressure" or "ccusage estimated cost/token burn" when exact plan accounting is unknown.
- When comparing models, compare both token volume and estimated cost. A model can have similar token volume but higher cost.
Output Shape
Use this structure unless the user asks otherwise:
- Short conclusion in plain language.
- Evidence table: total tokens, cost, input, output, cache create, cache read.
- Model comparison table.
- 5-hour block table when quota exhaustion is discussed.
- Explanation of why the burn happened.
- Confidence and caveats.
Keep the answer readable for non-technical users. Avoid unexplained terms like "cache read" without a one-sentence translation.
Version History
- c6903aa Current 2026-09-28 12:33
- e00a2ec 2026-08-20 11:26
