analytics

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Cross-Project Analytics

跨项目分析

Query local analytics data from

~/.claude/analytics/

. All data is local-only, privacy-safe (hashed project IDs, no PII).

从

~/.claude/analytics/

查询本地分析数据。所有数据仅存储在本地，隐私安全（项目ID已哈希处理，无个人可识别信息PII）。

Subcommands

子命令

Parse the user's argument to determine which report to show. If no argument provided, use AskUserQuestion to let them pick.

Subcommand	Description	Data Source	Reference
`agents`	Top agents by frequency, duration, model breakdown	`agent-usage.jsonl`	`references/jq-queries.md`
`models`	Model delegation breakdown (opus/sonnet/haiku)	`agent-usage.jsonl`	`references/jq-queries.md`
`skills`	Top skills by invocation count	`skill-usage.jsonl`	`references/jq-queries.md`
`hooks`	Slowest hooks and failure rates	`hook-timing.jsonl`	`references/jq-queries.md`
`teams`	Team spawn counts, idle time, task completions	`team-activity.jsonl`	`references/jq-queries.md`
`session`	Replay a session timeline with tools, tokens, timing	CC session JSONL	`references/session-replay.md`
`cost`	Token cost estimation with cache savings	`stats-cache.json`	`references/cost-estimation.md`
`trends`	Daily activity, model delegation, peak hours	`stats-cache.json`	`references/trends-analysis.md`
`summary`	Unified view of all categories	All files	`references/jq-queries.md`

解析用户参数以确定要显示的报告。如果未提供参数，使用AskUserQuestion让用户选择。

子命令	描述	数据源	参考文档
`agents`	按使用频率、时长、模型细分的热门Agent	`agent-usage.jsonl`	`references/jq-queries.md`
`models`	模型委托细分（opus/sonnet/haiku）	`agent-usage.jsonl`	`references/jq-queries.md`
`skills`	按调用次数排序的热门Skill	`skill-usage.jsonl`	`references/jq-queries.md`
`hooks`	最慢的Hook及失败率	`hook-timing.jsonl`	`references/jq-queries.md`
`teams`	团队生成次数、空闲时间、任务完成情况	`team-activity.jsonl`	`references/jq-queries.md`
`session`	重放包含工具、令牌、时间线的会话	CC session JSONL	`references/session-replay.md`
`cost`	含缓存节省的令牌成本估算	`stats-cache.json`	`references/cost-estimation.md`
`trends`	每日活动、模型委托、高峰时段	`stats-cache.json`	`references/trends-analysis.md`
`summary`	所有类别的统一视图	所有文件	`references/jq-queries.md`

Quick Start Example

快速入门示例

bash

undefined

bash

undefined

Top agents with model breakdown

带模型细分的热门Agent

jq -s 'group_by(.agent) | map({agent: .[0].agent, count: length}) | sort_by(-.count)' ~/.claude/analytics/agent-usage.jsonl

All-time token costs

全时段令牌成本

jq '.modelUsage | to_entries | map({model: .key, input: .value.inputTokens, output: .value.outputTokens})' ~/.claude/stats-cache.json

undefined

jq '.modelUsage | to_entries | map({model: .key, input: .value.inputTokens, output: .value.outputTokens})' ~/.claude/stats-cache.json

undefined

Quick Subcommand Guide

子命令快速指南

agents
,
models
,
skills
,
hooks
,
teams
,
summary
— Run the jq query from

references/jq-queries.md

for the matching subcommand. Present results as a markdown table.

session
— Follow the 4-step process in

references/session-replay.md

: locate session file, resolve reference (latest/partial/full ID), parse JSONL, present timeline.

cost
— Apply model-specific pricing from

references/cost-estimation.md

to CC's stats-cache.json. Show per-model breakdown, totals, and cache savings.

trends
— Follow the 4-step process in

references/trends-analysis.md

: daily activity, model delegation, peak hours, all-time stats.

summary
— Run all subcommands and present a unified view: total sessions, top 5 agents, top 5 skills, team activity, unique projects.

agents
,
models
,
skills
,
hooks
,
teams
,
summary
— 运行

references/jq-queries.md

中匹配子命令的jq查询，结果以Markdown表格呈现。

session
— 遵循

references/session-replay.md

中的4步流程：定位会话文件、解析引用（最新/部分/完整ID）、解析JSONL、呈现时间线。

cost
— 将

references/cost-estimation.md

中的模型特定定价应用于CC的stats-cache.json，显示按模型细分的成本、总成本及缓存节省。

trends
— 遵循

references/trends-analysis.md

中的4步流程：每日活动、模型委托、高峰时段、全时段统计。

summary
— 运行所有子命令并呈现统一视图：总会话数、Top 5 Agent、Top 5 Skill、团队活动、唯一项目数。

Data Files

数据文件

See

references/data-locations.md

for complete data source documentation.

File	Contents
`agent-usage.jsonl`	Agent spawn events with model, duration, success
`skill-usage.jsonl`	Skill invocations
`hook-timing.jsonl`	Hook execution timing and failure rates
`session-summary.jsonl`	Session end summaries
`task-usage.jsonl`	Task completions
`team-activity.jsonl`	Team spawns and idle events

完整的数据源文档请查看

references/data-locations.md

。

文件	内容
`agent-usage.jsonl`	包含模型、时长、成功状态的Agent生成事件
`skill-usage.jsonl`	Skill调用记录
`hook-timing.jsonl`	Hook执行时间及失败率
`session-summary.jsonl`	会话结束摘要
`task-usage.jsonl`	任务完成记录
`team-activity.jsonl`	团队生成及空闲事件

Rules

规则

Each category has individual rule files in

rules/

loaded on-demand:

Category	Rule	Impact	Key Pattern
Data Integrity	`rules/data-privacy.md`	CRITICAL	Hash project IDs, never log PII, local-only
Cost & Tokens	`rules/cost-calculation.md`	HIGH	Separate pricing per token type, cache savings
Performance	`rules/large-file-streaming.md`	HIGH	Streaming jq for >50MB, rotation-aware queries
Visualization	`rules/visualization-recharts.md`	HIGH	Recharts charts, ResponsiveContainer, tooltips
Visualization	`rules/visualization-dashboards.md`	HIGH	Dashboard grids, stat cards, widget registry

Total: 5 rules across 4 categories

每个类别在

rules/

目录下有单独的规则文件，按需加载：

类别	规则	影响级别	关键模式
数据完整性	`rules/data-privacy.md`	关键	哈希项目ID，绝不记录PII，仅本地存储
成本与令牌	`rules/cost-calculation.md`	高	按令牌类型区分定价，缓存节省
性能	`rules/large-file-streaming.md`	高	对>50MB文件使用流式jq查询，支持轮换文件查询
可视化	`rules/visualization-recharts.md`	高	Recharts图表、ResponsiveContainer、工具提示
可视化	`rules/visualization-dashboards.md`	高	仪表板网格、统计卡片、小部件注册表

总计：4个类别下的5条规则

References

参考文档

Reference	Contents
`references/jq-queries.md`	Ready-to-run jq queries for all JSONL subcommands
`references/session-replay.md`	Session JSONL parsing, timeline extraction, presentation
`references/cost-estimation.md`	Pricing table, cost formula, daily cost queries
`references/trends-analysis.md`	Daily activity, model delegation, peak hours queries
`references/data-locations.md`	All data sources, file formats, CC session structure

参考文档	内容
`references/jq-queries.md`	适用于所有JSONL子命令的可直接运行的jq查询
`references/session-replay.md`	会话JSONL解析、时间线提取、呈现
`references/cost-estimation.md`	定价表、成本公式、每日成本查询
`references/trends-analysis.md`	每日活动、模型委托、高峰时段查询
`references/data-locations.md`	所有数据源、文件格式、CC会话结构

Important Notes

重要说明

All files are JSONL (newline-delimited JSON) format
For large files (>50MB), use streaming
```
jq
```
without
```
-s
```
— see
```
rules/large-file-streaming.md
```
Rotated files:
```
<name>.<YYYY-MM>.jsonl
```
— include for historical queries
```
team
```
field only present during team/swarm sessions
```
pid
```
is a 12-char SHA256 hash — irreversible, for grouping only

所有文件均为JSONL（换行分隔JSON）格式
对于大文件（>50MB），使用不带
```
-s
```
的流式
```
jq
```
— 详见
```
rules/large-file-streaming.md
```
轮换文件：
```
<name>.<YYYY-MM>.jsonl
```
— 查询历史数据时需包含这些文件
```
team
```
字段仅在团队/集群会话中存在
```
pid
```
是12位SHA256哈希 — 不可逆，仅用于分组

Output Format

输出格式

Present results as clean markdown tables. Include counts, percentages, and averages. If a file doesn't exist, note that no data has been collected yet for that category.

结果以清晰的Markdown表格呈现，包含计数、百分比和平均值。如果文件不存在，需注明该类别尚未收集数据。