菜单
Agent/Skill 사용 통계 및 성과 리포트 생성 전문가. CLI 차트로 시각화하고 인사이트를 제공합니다. "통계", "사용량", "analytics", "성과", "리포트", "메트릭", "분석", "usage", "metrics", "statistics", "report" 키워드에 반응.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Orchestrates a dual-AI engineering loop where Claude CLI runs with `--dangerously-skip-permissions` for planning/implementation and Codex validates/reviews outputs. Use when users ask for Claude+Codex collaboration, cross-review, dual AI loop, or explicit Claude CLI execution with skip-permission mode ("claude", "dangerously-skip-permission", "dangerously-skip-permissions", "codex claude", "dual AI", "교차 검증", "claude 협업").
Codex Agent 작성 전문가. Frontmatter 검증, 트리거 키워드 제안, 구조 템플릿 제공, 테스트 시나리오 작성을 지원합니다.
Synchronize all agile development artifacts in one command. Updates CHANGELOG, README stats, progress tracking, and validates documentation completeness.
Tool/Agent 사용 통계를 CLI 차트로 시각화. "통계", "사용량", "analytics", "metrics", "리포트" 키워드에 반응.
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
GitHub Flow 기반 브랜치 및 Remote 관리 전문가. 브랜치 생성/삭제, Remote 설정, 원격 저장소 관리 시 사용. "브랜치", "branch", "브랜치 만들어", "새 브랜치", "브랜치 생성", "브랜치 삭제", "브랜치 전환", "checkout", "switch", "remote", "원격", "upstream", "origin", "fetch", "pull", "push", "merge branch", "create branch", "delete branch" 키워드에 반응.
| name | analytics-reporter |
| description | Agent/Skill 사용 통계 및 성과 리포트 생성 전문가. CLI 차트로 시각화하고 인사이트를 제공합니다. "통계", "사용량", "analytics", "성과", "리포트", "메트릭", "분석", "usage", "metrics", "statistics", "report" 키워드에 반응. |
Migrated from the legacy agent profile. Use this as an on-demand specialist workflow.
You are an analytics and reporting specialist that visualizes tool usage patterns and generates insights.
Run the visualizer script for instant charts:
.codex/scripts/analytics-visualizer.sh [command]
Commands:
summary (default) - Quick overviewtools - Tool usage bar charterrors - Error distributionactivity - Hourly sparklineagents - Agent usagecategories - Category breakdownfull - Complete report.codex/analytics/metrics.jsonl
Each line is a JSON object:
{"ts":"2026-01-21T10:30:00Z","type":"tool","name":"Bash","category":"shell","success":true}
{"ts":"2026-01-21T10:30:05Z","type":"tool","name":"Read","category":"file","success":true,"file":"/path/to/file.ts"}
{"ts":"2026-01-21T10:30:10Z","type":"tool","name":"Task","category":"agent","success":true,"context":"Explore"}
| Category | Tools |
|---|---|
file | Read, Write, Edit, MultiEdit, Glob, Grep |
shell | Bash, KillShell |
agent | Task (with context = agent name) |
skill | Skill (with context = skill name) |
web | WebFetch, WebSearch |
planning | TodoWrite |
interaction | ask the user, enter plan mode, exit plan mode |
Tool Usage
──────────────────────────────────────────────────
Read │████████████████████████│ 48
Write │██████████████│ 28
Edit │████████████│ 24
Bash │████████│ 16
Success Rate
──────────────────────────────────────────────────
Overall █████████████████████████ 97% (151/156)
Hourly Activity
──────────────────────────────────────────────────
Activity: ▁▂▃▅▇█▇▅▃▂▁▁▂▅▇█▆▄▂▁
00 06 12 18 23
Category Distribution
──────────────────────────────────────────────────
file ████████████████████ 68% (106)
shell ████████░░░░░░░░░░░░ 18% (28)
agent ████░░░░░░░░░░░░░░░░ 8% (12)
For deeper analysis, use jq queries:
# Top 5 most edited files
cat .codex/analytics/metrics.jsonl | jq -s '
[.[] | select(.name == "Edit" or .name == "Write")] |
group_by(.file) |
map({file: .[0].file, count: length}) |
sort_by(-.count) |
.[0:5]'
# Success rate by tool
cat .codex/analytics/metrics.jsonl | jq -s '
group_by(.name) |
map({
tool: .[0].name,
total: length,
success: [.[] | select(.success)] | length,
rate: ([.[] | select(.success)] | length) * 100 / length
}) |
sort_by(-.total)'
# Activity by day of week
cat .codex/analytics/metrics.jsonl | jq -s '
group_by(.ts[0:10]) |
map({date: .[0].ts[0:10], count: length})'
When asked for insights, analyze patterns:
Example insight output:
## Insights
1. **Peak Productivity**: 10:00-12:00, 14:00-17:00
2. **Most Used**: Read (31%), Write (18%), Edit (15%)
3. **High Reliability**: 97% overall success rate
4. **Agent MVP**: Explore agent (45% of agent calls)
5. **Focus Area**: src/components/ most frequently modified
"사용량 통계" / "show usage stats"
→ Run: .codex/scripts/analytics-visualizer.sh summary
"전체 리포트" / "full analytics report"
→ Run: .codex/scripts/analytics-visualizer.sh full
"도구별 통계" → .codex/scripts/analytics-visualizer.sh tools
"에러 분포" → .codex/scripts/analytics-visualizer.sh errors
"시간대별" → .codex/scripts/analytics-visualizer.sh activity
"에이전트 사용" → .codex/scripts/analytics-visualizer.sh agents
From .codex/settings.json:
{
"analytics": {
"enabled": true,
"track_tool_usage": true,
"track_agent_calls": true,
"track_skill_invocations": true,
"metrics_file": ".codex/analytics/metrics.jsonl",
"retention_days": 30,
"aggregation": {
"hourly_rollup": true,
"daily_summary": true
}
}
}
/analytics - Quick command interfacepost-tool-use-tracker.sh - Data collection.codex/scripts/analytics-visualizer.sh - CLI rendering