플러그인

DeepSeek Harness ctx.web용 SearXNG 검색 및 Scrapling 다단계 가져오기 제공자 번들입니다. SSRF 보호와 Markdown 변환을 지원합니다.

DeepSeek Harness 클라이언트 플러그인: Models 설정 섹션의 fetch-models 대화상자에 '선택 반전' 버튼을 추가하여, 두 번째 fetch + add 단계에서 이미 모델 목록에 있는 행만 체크된 상태로 남도록 합니다.

회사명이나 티커를 SEC EDGAR를 통해 검증된 주식 심볼로 해석한 뒤, yahoo-finance2에서 가격, P/E, EPS, 시가총액, 52주 범위, 배당 수익률을 포함한 실시간 시세를 가져옵니다.

DSH용 Modellix 통합: 분할 Design 워크스페이스에서 스키마 기반 이미지, 비디오, 오디오 생성, 실시간 LLM 모델 카탈로그, 하나의 API 키로 네이티브 웹 검색 및 fetch provider를 제공합니다.

DeepSeek Harness용 경제학 우선 저널/워킹페이퍼 모니터: NBER RSS + arXiv econ(4개 카테고리) + 중국 경제학 저널(Shi Jie Jing Ji는 Magtech 경유, Zhong Guo Nong Cun Guan Cha, Cai Mao Jing Ji, Zhong Guo Ren Kou Ke Xue, Jing Ji Guan Li는 ajcass 경유) 수집, 키워드 필터, 드라이런/Webhook 푸시, 중복 제거 영속화, schedule_create 호환 브리핑.

DSH 설정 페이지에 「用量」 섹션을 추가하여 MiniMax Token Plan 사용량(5시간 및 주간 윈도우 리셋 카운트다운), 모델별 내역, 비디오 보너스 크레딧을 표시합니다. API 키를 보유한 신뢰할 수 있는 플러그인을 통해 `/v1/token_plan/remains`를 가져오며, 키가 설정되지 않은 경우 자동으로 숨겨집니다. MIT.

DeepSeek Harness 웹 능력 시음(ctx.web)을 위한 Firecrawl 기반 검색 및 페치 프로바이더

최소 프롬프트 × Web PTC 기능: 한 줄 페르소나, run_code SDK, 서브에이전트, Ralph, 웹 검색/가져오기, Windows Git Bash. 범용 워크플로 도구는 숨겨진 상태로 유지.

SXS의 프로덕션 스크래핑 스택(일일 수백만 요청)으로 강화된 안티봇 HTTP 페치 도구: UA 풀 회전, 지수 백오프 재시도, 안티봇 월 감지(캡차/검증 챌린지), 적응형 레이트 리미팅 — 도구: `sxs_fetch` / `sxs_fetch_json` / `sxs_rate_status`.

composer stats 행에 실시간 session token usage와 estimated cost를 표시하며, pricing은 DeepSeek 공식 pricing 페이지에서 가져옵니다.

DeepSeek Harness용 구조화된 안전한 Git 도구 모음: status/diff/log/branch/stage/commit/stash/show/fetch/pull/remote/checkout, 파괴적 명령 가드 포함

DSH 插件：web_focus 工具按关键词对抓取页面做相关度筛选，压缩链接、过滤导航、保留可回取的原文并缓存，让 web_fetch 不再一次性消耗大量token。

Git workbench in the DSH session header and overlay: view changes, commit, fetch, pull, push, and browse branches and history in existing local repositories.

Web search and fetch provider for DeepSeek Harness and Pi: anonymous-first routing across Exa, Tavily, Parallel, Firecrawl and TinyFish, with opt-in billing, quota preflight and bounded cancellation.

Union web search for DSH (consolidated successor of DDDMUC/dsh-free-search, which it credits): 28 engines across three tiers — keyless free (Bing/DuckDuckGo/AnySearch/SearXNG multi-instance union, plus Exa/Tavily/Keenable/Firecrawl/Parallel keyless modes), paid-with-key (Zhihu/Perplexity/Serply/DeepSeek official/You.com/Baidu/Kimi/Aliyun/Doubao/Zhipu/Bocha/Metaso), and model built-in search (OpenAI/Gemini/Claude/Grok, explicit opt-in only) — with auto smart routing, per-engine enable/disable & fallback priority, parallel top-3 merge, multi_search, failure-aware fallback, a toggle to block the system built-in search, time filtering, platform search, web_fetch and a web settings UI. Experimental free advance_fetch: whole-page GFM-Markdown or CSS-selector/fields structured extraction with no API key and no per-call billing; fetch identity configurable (custom User-Agent, Referer, per-domain cookies attached only on domain match, never leaked across cross-domain redirects). Hosts 0.1.0-rc.2 through 0.2.1-rc.2 (17-tag exact engines.dsh enum; the rc.2 search-provider takeover goes through volatile config pinning after capability probing, never version branches). Paid engines need your own API keys (optional; free engines work keyless). npm: @drscrewdriver/dsh-union-search and bare dsh-union-search.

Composer pill with the DeepSeek account balance, the live peak/off-peak pricing phase, and this session's spend priced request by request at the rate in effect when each request was sent. Subagent sessions' costs are aggregated into the parent session; Search and Fetch fees are charged only for DeepSeek's search engine, while third-party engines (Tavily, Bing, Exa, …) are counted but free. The balance refresh interval is configurable.

Routes DSH web search and fetch through configured providers and records per-attempt usage and estimated costs. Requires Node.js >=22.19 and DSH 0.2.1-rc.2.

Git repository connector for DeepSeek Harness: saved repo profiles addressed by name, work-copy operations (clone/fetch/pull/push/commit), Gitea/Forgejo/GitHub API tools, keys in the DSH credential center, and per-repo safety flags (TLS bypass, overwrite, force push).

Watches the foreground browser window, recognizes video courses, classifies them by subject, fetches Bilibili metadata/danmaku/comments, and generates Markdown + Mermaid knowledge maps and Word study manuals.

9router-backed web search + fetch providers for DeepSeek Harness (ctx.web). Wires the native web_search/web_fetch tools to 9router's /v1/search and /v1/web/fetch endpoints.

Fetch academic papers by DOI or keyword: Crossref and OpenAlex search, batch PDF download through eight Sci-Hub mirrors with an Unpaywall open-access fallback, PDF magic-byte validation, bounded concurrency, and a clickable batch-access HTML manifest for papers that could not be downloaded.

Registers external databases and document corpora as callable model tools: a per-source access boundary, a credential reference ledger that never stores values, and a fetch ledger that keeps fingerprints and content hashes instead of payloads.

TinyFish-backed search and fetch providers for the DeepSeek Harness web capability seam (ctx.web) — $0 SERP and page extraction, direct or via Monid.

Headless Playwright fetch (title + body text) in WSL.