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 skills add SW-in-beta/simon-skills --skill simon-oncallgit clone --depth 1 https://github.com/SW-in-beta/simon-skillsWrote 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/sw-in-beta/simon-skills/simon-oncall)<a href="https://agentmods.dev/skills/sw-in-beta/simon-skills/simon-oncall"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-oncall/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sw-in-beta/simon-skills/simon-oncall"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-oncall.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00187 | $0.04201 |
| Opus 5 | $0.00093 | $0.02100 |
| Sonnet 5 | $0.00037 | $0.00840 |
| Haiku 4.5 | $0.00019 | $0.00420 |
Grade A, and why
simon-oncall scanned grade A with 0 findings 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 10d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
simon-oncall
온콜 문의 분석 스킬. 슬랙으로 들어온 기술 문의를 파악하고, 관련 코드와 사내 자료를 심층 분석(simon-study) → 원인/해결 방향 → 슬랙 답변 초안까지 제공합니다.
자율주행모드 ON 입니다. 여러 Agent와 병행하여 딥하게 조사해주세요. 이 선언은 CLAUDE.md의 모호성 확인 규칙보다 우선한다 — 분석 진행 중 세부 모호함은 스스로 판단해 진행한다. 단, 분석 대상 자체(코드/레포/질문)가 특정되지 않는 수준의 모호함은 시작 전 1회만 확인한다.
Why this exists
온콜 문의는 대부분 "이거 왜 이런 거야?", "이게 현재 가능할까요?" 형태입니다. 좋은 답변을 하려면 슬랙 맥락 파악 → 최신 코드 분석 → 사내 문서/논의 검색 → 종합 판단이 필요한데, 이 과정을 체계적으로 수행합니다.
Input
사용자가 제공하는 것:
- 슬랙 URL — 온콜 문의 메시지 (buzzvil.slack.com)
- 레포 이름 (선택) — 관련 서비스의 레포지토리 (~/buzzvil/{repo_name}에 위치)
슬랙 URL이 빠져 있으면 요청합니다.
레포 이름이 빠져 있으면 references/repo-map.md를 참조하여 문의 키워드로 관련 레포를 추천합니다.
추천이 명확하지 않을 때만 사용자에게 확인합니다.
Instructions
진행 체크포인트: 각 Phase 경계에서 1줄 진행 보고를 출력한다 — [Phase N 완료] {핵심 결과 요약} — Phase N+1 시작 형식. 장시간 무응답 구간에서 사용자가 진행 상태를 알 수 있게 한다 (AskUserQuestion 아님, 단순 텍스트).
Phase 1: 문의 파악
슬랙 스레드를 읽고 문의의 핵심을 파악합니다.
~/.claude/skills/buzzvil-slack/scripts/fetch_thread.sh "{slack_url}" --resolve-users
단일 메시지(스레드 없음)라면:
~/.claude/skills/buzzvil-slack/scripts/fetch_message.sh "{slack_url}"
스레드에서 추출할 것:
- 문의자: 누가 물어봤는가
- 핵심 질문: 한 문장으로 요약
- 문의 유형:
ERROR— 에러/장애 ("왜 500이 나와요?", "이거 깨졌어요")DATA_ANOMALY— 데이터 이상 ("수치가 이상해요", "왜 0이 나오지?")LOGIC_INQUIRY— 로직/동작 질문 ("이 로직이 왜 이렇게 동작해요?")CAPABILITY— 기능 가능 여부 ("이런 게 가능할까요?")
- 추가 맥락: 이미 논의된 내용, 첨부 스크린샷/로그, 언급된 키워드
사용자에게 파악한 내용을 간단히 확인합니다:
"문의 내용을 이렇게 이해했습니다: [요약]. 맞나요?"
Phase 1.5: 레포 특정
사용자가 레포를 명시하지 않았으면 references/repo-map.md를 읽고, Phase 1에서 파악한 키워드와 대조하여 관련 레포를 특정합니다.
- 매핑이 명확하면 (1개 레포로 좁혀지면) 바로 진행하고 사용자에게 알림: "관련 레포로 {repo_name}을 선택했습니다"
- 후보가 2-3개면 사용자에게 선택지 제시: "A, B, C 중 어디를 먼저 볼까요?"
- 로컬에 레포가 없으면 클론:
gh repo clone Buzzvil/{repo_name} ~/buzzvil/{repo_name} -- --depth 1
Phase 2: 레포 준비
최신 master(또는 main) 브랜치 기준으로 분석해야 합니다.
cd ~/buzzvil/{repo_name}
git fetch origin
# master 우선, 없으면 main
git checkout master 2>/dev/null || git checkout main
git pull origin $(git branch --show-current)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 281 lines · 187 tokens per session scan A a17dfda29153
simon-oncall is a skill published in the GitHub repository SW-in-beta/simon-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 187 tokens to every session and 4,201 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.