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 mupengi-bot/mupengism --skill web-claudegit clone --depth 1 https://github.com/mupengi-bot/mupengismWrote 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/mupengi-bot/mupengism/web-claude)<a href="https://agentmods.dev/skills/mupengi-bot/mupengism/web-claude"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/web-claude/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/mupengi-bot/mupengism/web-claude"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/web-claude.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 | $0.00043 | $0.01813 |
| Opus 5 | $0.00022 | $0.00907 |
| Sonnet 5 | $0.00009 | $0.00363 |
| Haiku 4.5 | $0.00004 | $0.00181 |
Grade A, and why
web-claude 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unified Web Search — 통합 웹 검색 🐧
3단계 fallback 전략으로 안정적인 웹 검색 제공: Brave API → DuckDuckGo → claude.ai 브라우저
검색 전략
1차: web_search (Brave API) — ⚡ 빠르고 안정적 (권장)
OpenClaw 내장 web_search tool 사용.
web_search(query="검색어", count=5, freshness="pw")
장점:
- 빠른 응답 (1-2초)
- 구조화된 JSON 결과
- freshness 파라미터 지원 (pd=24h, pw=1주, pm=1개월)
- search_lang, country 파라미터로 한국어/지역 검색 가능
단점:
- Brave API 키 필요
- 키 없으면
missing_brave_api_key에러
2차: duckduckgo-search — 🔒 프라이버시 중심 (fallback)
Brave 실패 시 DuckDuckGo API 사용.
python -c "
from duckduckgo_search import DDGS
with DDGS() as ddgs:
results = list(ddgs.text('검색어', region='wt-wt', max_results=5))
for r in results:
print(f\"{r['title']}: {r['href']}\")
"
장점:
- API 키 불필요
- 프라이버시 친화적
- 다양한 검색 타입 (text, news, images, videos)
단점:
- 결과 품질이 Brave보다 낮음
- 요청 제한 있음 (너무 빠르게 연속 요청 시 차단)
3차: web-claude (브라우저) — 🧠 분석+검색 (최후 수단)
claude.ai 브라우저 탭에서 웹 검색 트리거.
1. browser navigate → https://claude.ai/new
2. browser act type → "검색 질문"
3. browser act press → Enter
4. sleep 15-30초
5. browser snapshot → 응답 추출
장점:
- API 키 불필요
- claude.ai가 자동으로 웹 검색 + 분석 + 요약
- 복잡한 리서치에 유용
단점:
- 느림 (15-30초)
- 브라우저 필요 (포트 18800, openclaw 프로필)
- 일일 메시지 제한 (무료 계정)
- 자동화 감지 리스크
자동 fallback 로직
if web_search available:
try web_search(query)
if success: return results
if web_search failed or unavailable:
try duckduckgo-search
if success: return results
if both failed:
fallback to web-claude browser method
검색 결과 자동 캐시
모든 검색 결과는 memory/research/ 폴더에 자동 저장:
파일명 규칙:
memory/research/search-YYYY-MM-DD-HH-MM-[키워드].md
저장 내용:
- 검색 쿼리
- 타임스탬프
- 사용된 검색 방법 (Brave/DuckDuckGo/claude.ai)
- 검색 결과 (링크 + 요약)
- 추출된 인사이트
예시:
# Web Search: AI 에이전트 시장 규모
- **검색 시각:** 2026-02-14 07:56 KST
- **검색 방법:** web_search (Brave API)
- **쿼리:** "AI 에이전트 시장 규모 2026년"
## 결과
1. **AI Agent Market to Reach $47B by 2030** - TechCrunch
https://techcrunch.com/...
- CAGR 43.2% 성장 전망
- 기업용 에이전트가 60% 차지
2. **한국 AI 시장 1조 원 돌파** - 조선일보
https://chosun.com/...
- 2026년 1분기 기준
- 생성형 AI가 주도
...
## 인사이트
- AI 에이전트 시장은 빠르게 성장 중
- 기업용 자동화가 핵심 동력
- 한국 시장도 활발
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 · 250 lines · 43 tokens per session scan A cd9f5fc04cae
web-claude is a skill published in the GitHub repository mupengi-bot/mupengism (10 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,813 once invoked, about $0.0002 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
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…