Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/intellieffect/agentic-cms/traffic-reportnpx skills add intellieffect/agentic-cms --skill traffic-reportgit clone --depth 1 https://github.com/intellieffect/agentic-cmsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/intellieffect/agentic-cms/traffic-report)<a href="https://agentmods.dev/skills/intellieffect/agentic-cms/traffic-report"><img src="https://agentmods.dev/badge/skills/intellieffect/agentic-cms/traffic-report.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00119 | $0.05748 |
| Opus 5 | $0.00060 | $0.02874 |
| Sonnet 5 | $0.00024 | $0.01150 |
| Haiku 4.5 | $0.00012 | $0.00575 |
Grade A, and why
traffic-report scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bash 단일 호출에 `&` + `wait` 패턴으로 fan-out. 각 curl은 30s timeout, `-o`로 임시 파일 저장, `-w`로 HTTP 코드 캡처. How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
traffic-report — agentic-cms 트래픽 헤비 리포트
dashboard /analytics/traffic 가 제공하는 3소스(self analytics_events + GA4 + GSC) 데이터를 한 호출로 병렬 수집하고, 룰 기반 해석·이상 감지·행동 제안을 대화창 markdown 한 장으로 출력한다.
설계 원칙:
- 기존
dashboard/src/app/api/analytics/*/route.ts+dashboard/src/lib/analytics/traffic.ts계산 로직을 100% 재사용. 이 스킬은 얇은 HTTP 클라이언트 + 해석 레이어. - dashboard 서버 기동 전제. 미기동이면 기동 안내만 하고 종료 (자동 기동 금지).
- 파일 저장·옵시디언 반영 없음. 인라인 출력만.
인자 규약
| 호출 | 의미 |
|---|---|
/traffic-report |
기본. preset=7d + today 스냅샷 + GA4·GSC(env 있으면) + 30d 히스토리 렌즈 |
/traffic-report 7d|30d|90d|this_month|last_month |
preset 지정 |
/traffic-report today |
오늘 누적(KST) vs 어제 동시점까지 비교 |
/traffic-report --compare=none |
비교 끔 (현재 값만) |
/traffic-report --skip=ga4,gsc |
외부 소스 스킵 (GA4/GSC env 미설정 시 자동 스킵) |
/traffic-report --topn=N |
breakdown 상위 N (기본 10, API 상한 25) |
preset이 30d·90d·this_month·last_month 또는 today이면 30일 히스토리 렌즈 섹션은 생략 (중복·의미 없음).
Phase 0 — Preflight
아래를 순서대로 확인. 실패 시 Phase 1 진입 금지.
0-1. 포트 3150 LISTEN
lsof -iTCP:3150 -sTCP:LISTEN -n -P 2>/dev/null | grep LISTEN
출력 없으면 기동 안내 후 스킬 종료 (자동 기동 X):
dashboard가 기동되지 않았습니다. 아래 명령으로 먼저 기동해 주세요.
cd /Users/jinkihyeok/Projects/agentic-cms/dashboard && PORT=3150 npm run dev
0-2. 인자 파싱 · 기본값 확정
- preset: 기본
7d.today면 mode=today. - compare: 기본
previous.--compare=none이면none. - topN: 기본 10.
--topn=N오면 1~25 clamp. - skip 목록:
--skip=ga4,gsc쉼표 분리.
0-3. GA4 / GSC 기본 포함 · 500이면 자동 degrade
GA4·GSC는 항상 호출 시도. Phase 1에서 500/503 응답 오면 해당 섹션만 "[데이터 없음: env 미설정]"로 degrade (사용자에게 env.local 설정 안내 bullet 추가). --skip=ga4 또는 --skip=gsc 명시하면 호출 자체 생략.
dashboard가 살아있으면 Supabase 연결은 일반적으로 정상 (서버가 이미 env 로드 상태). main API가 500이면 그때 전체 중단 + 에러 메시지.
Phase 1 — 병렬 수집
bash 단일 호출에 & + wait 패턴으로 fan-out. 각 curl은 30s timeout, -o로 임시 파일 저장, -w로 HTTP 코드 캡처.
BASE=http://localhost:3150
TMPDIR=$(mktemp -d)
PRESET={preset}
COMPARE={compare}
TOPN={topN}
DAYS={mapped_days} # preset→days: 7d→7 / 30d→30 / 90d→90 / this_month·last_month→30 / today→7
# 주 데이터 (compare 또는 today)
if [ "$PRESET" = "today" ]; then
URL_MAIN="$BASE/api/analytics/traffic?mode=today&topN=$TOPN"
else
URL_MAIN="$BASE/api/analytics/traffic?mode=compare&preset=$PRESET&compare=$COMPARE&topN=$TOPN"
fi
curl -sS --max-time 30 -o "$TMPDIR/main.json" -w "%{http_code}" "$URL_MAIN" > "$TMPDIR/main.code" &
# today 스냅샷 (preset≠today일 때만, 리포트 상단에 "지금 이 순간" pulse로)
if [ "$PRESET" != "today" ]; then
curl -sS --max-time 30 -o "$TMPDIR/today.json" -w "%{http_code}" "$BASE/api/analytics/traffic?mode=today&topN=$TOPN" > "$TMPDIR/today.code" &
fi
# 30d 히스토리 렌즈 (preset=7d 일 때만)
if [ "$PRESET" = "7d" ]; then
curl -sS --max-time 30 -o "$TMPDIR/lens30.json" -w "%{http_code}" "$BASE/api/analytics/traffic?mode=compare&preset=30d&compare=previous&topN=$TOPN" > "$TMPDIR/lens30.code" &
fi
# GA4 (--skip=ga4 아닐 때만, 500이면 Phase 2에서 degrade)
if [ "$SKIP_GA4" != "1" ]; then
curl -sS --max-time 30 -o "$TMPDIR/ga4.json" -w "%{http_code}" "$BASE/api/analytics/ga4?days=$DAYS" > "$TMPDIR/ga4.code" &
fi
# GSC (--skip=gsc 아닐 때만, 500이면 Phase 2에서 degrade)
if [ "$SKIP_GSC" != "1" ]; then
curl -sS --max-time 30 -o "$TMPDIR/gsc.json" -w "%{http_code}" "$BASE/api/analytics/gsc?days=$DAYS" > "$TMPDIR/gsc.code" &
fi
wait
echo "tmpdir=$TMPDIR"
for f in main today lens30 ga4 gsc; do
[ -f "$TMPDIR/$f.code" ] && echo "$f=$(cat $TMPDIR/$f.code)"
done
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 382 lines · 119 tokens per session scan A a8488cd32945
traffic-report is a skill published in the GitHub repository intellieffect/agentic-cms (0 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 5,748 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…