Borrowing it
Nothing to install: this file belongs to tobyilee/book-writer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tobyilee/book-writer/main/.claude/skills/web-research/SKILL.mdgit clone --depth 1 https://github.com/tobyilee/book-writerWrote 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/tobyilee/book-writer/web-research)<a href="https://agentmods.dev/skills/tobyilee/book-writer/web-research"><img src="https://agentmods.dev/badge/skills/tobyilee/book-writer/web-research.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.00818 |
| Opus 5 | $0.00040 | $0.00409 |
| Sonnet 5 | $0.00016 | $0.00164 |
| Haiku 4.5 | $0.00008 | $0.00082 |
Grade A, and why
web-research 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 7d 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.
What it actually says
Web Research
주제 관련 일반 웹 자료(블로그, 기사, 공식 문서, 튜토리얼)를 수집한다. 논문과 커뮤니티는 별도 에이전트가 맡으므로 중복 수집하지 않는다.
절차
- 검색 키워드 설계 — 주제에서 3~5개 키워드 조합 생성 (한국어 + 영어)
- 검색 실행 — 우선순위:
- Firecrawl 스킬 (가능 시) — 전문 추출·인덱싱에 강함
- WebSearch 도구 → 상위 결과 링크 수집
- WebFetch 도구 → 각 페이지 본문 가져오기
- 소스 평가 — 신뢰성 등급 매기기
- 최상: 공식 문서·릴리스 노트·체인지로그, RFC/스펙, GitHub 릴리스, 기술 저널, 회사 엔지니어링 블로그(우아한형제들·카카오·토스·네이버 D2·LINE·Netflix·Cloudflare 등), 확인된 저자 블로그
- 중: 커뮤니티 블로그, 포털 기술 아티클, 컨퍼런스 발표 트랜스크립트, 기술 뉴스레터(긱뉴스 등)
- 하: 출처 불명 나열형 아티클, 날짜 없는 글 (가능하면 제외)
- 버전·API·수치는 공식 1차 소스(릴리스 노트·공식 문서) 우선 — fact-checker 대조 기준이 된다
- 추출 — 각 자료에서 핵심 주장, 인용 가능한 구절, 수치 발췌
- 저장 —
{slug}/research/web.md
수집 가이드
- 목표 건수: 8~15건 (주제 폭에 따라 조정)
- 다양성: 한 사이트 최대 2건, 한 저자 최대 2건
- 최신성: 최근 3년 내 자료 비중을 높이되, 고전 레퍼런스도 1~2건 포함
- 언어 비율: 대상 독자가 한국이면 한국어 60~70%, 글로벌이면 영어 70%+
- 인용 원문 보존: 요약하지 말고 구절을 그대로 가져와 따옴표 처리
출력 형식
# 웹 리서치: {주제}
## 자료 1: {제목}
- 출처: {URL}
- 저자·날짜: {...}
- 신뢰성: {최상/중/하}
- 핵심 주장: {2~3문장}
- 인용 가능한 구절:
> "..."
- 관련 섹션: (레퍼런스 문서 어느 섹션에 쓸지 힌트)
## 자료 2: ...
## 수집 한계
- 접근 실패한 자료: ...
- 의도적으로 제외한 소스 유형: ...
실패 대응
- 검색 결과 빈약 → 키워드 변형 (동의어, 영문 번역, 약어 ↔ 풀네임) 후 재시도
- 특정 페이지 접근 실패 → 해당 자료 제외, 로그에 기록
- Firecrawl·WebSearch 모두 실패 → 캐시된 아카이브(archive.org) 활용 시도
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.
- 7d ago First seen · 59 lines · 80 tokens per session scan A 0a5db55a5a34
web-research is a skill published in the GitHub repository tobyilee/book-writer (81 stars, last pushed 21d ago), licensed MIT. It adds 80 tokens to every session and 818 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…