플러그인

Remote-SSH 스타일 워크스페이스: SSH 호스트와 원격 디렉터리를 네이티브 DSH 워크스페이스로 전환합니다. 에이전트는 12개의 rw_* 도구(SFTP/exec)를 통해 원격 파일 시스템을 직접 조작하며, 워크스페이스로 제한된 경로와 known_hosts 검증을 사용합니다.

DSH 에이전트용 검증 게이트: 완료 게이트가 목표를 통과시키기 전에 모든 수락 기준이 서버 스탬프가 찍힌 실제 도구 증거로 뒷받침되어야 함(자문 감사, 강제 게이트, 영구 허가).

Xiaohongshu/RED 바이럴 노트 에이전트 스킬 번들: 인기 노트 조사, 노트 생성/재작성, 검증, 인증된 계정 분석, QR 로그인 및 제어된 게시.

DSH용 증거 기반 기업 및 채용 실사: 증거 수준과 함께 출처를 기록하고, 증거로 범위가 제한된 주장을 추가하며, 공식 등기부로 법인 실체를 검증하고, 검증 체크리스트와 면접 질문이 포함된 PROCEED/VERIFY/STOP 보고서를 렌더링합니다.

DeepSeek Harness(dsh)용 Rust 개발 도메인 플러그인: 검증 피라미드 fmt→clippy→build+test→miri+audit(+semver)를 모델 대상 도구로 제공 + 그래프 계층 거버넌스(anti-Goodhart 8가지 규칙: #[allow] 밀도 / 삭제된 테스트 포함, Cargo.toml 및 pub을 통한 blind-spot

DeepSeek Harness(dsh)용 Linux 커널 개발 도메인 플러그인: 검증 피라미드 L1-L4를 모델 대상 도구로 제공 + 그래프 계층 거버넌스(anti-Goodhart / blind-spot / patch-conflict) + AGENTS.md 계약을 시스템 프롬프트 섹션으로 사용. 순수 JS, 빌드 단계 없음.

dsh용 spec-driven 개발 규율: 5개의 keel 스킬(anchor/spec/probe/build/audit), 3개의 리뷰 도구, 6개의 spec 템플릿이 코드보다 먼저 명세를 쓰는 것, 가정 검증, 범위 통제를 강제합니다.

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`.

에이전트 산출물을 위한 독립 브라우저 승인 테스트입니다. JSON 사양을 입력하면 실제 Chromium 판정이 출력됩니다.

실제 연산 검증 게이트: 수식 단순화, 논리 증명, 정규식 검증, E-prover FOL, 상태 머신 검사, 코드 복구, Go로 컴파일된 바이너리 기반(미리 빌드된 Windows 실행 파일 포함)

DSH GUI Toolkit — Windows desktop control tools for DeepSeek Harness (DSH): screen layout, annotated screenshot, single-window capture, click / drag / type / key / scroll, semantic verification, window management, and UI Automation structured queries. Thi

Cordis-native, evidence-driven full-stack engineering workflow: inspect-first planning, explicit verification evidence, and approval-aware gating for sensitive operations.

SMS forwarding webhook for DeepSeek Harness. Phone apps (SMS Forwarder, Tasker, or any HTTP POST) push messages to a local HTTP endpoint; the plugin stores them as JSONL and exposes sms_recent / sms_search tools so the agent can read SMS verification codes during tasks. Auto-extracts the first 4-8 digit OTP from each message, supports keyword filtering, and works over LAN or Tailscale.

DeepSeek Harness용 TypeSafe Jev(System One 의사결정 모델) 엔드투엔드 통합: jev_decision(choice/score/noul, 병렬, 타입 지정 답변 + 신뢰도), API 키와 스위치를 위한 Settings > Plugins 카드, 대화의 모든 결정(답변, 신뢰도, 지연 시간, 비용)을 보여주는 인라인 도구 뷰, 자동 가드(결정적 + Jev 위험/루프 점검), 로컬 /jev 대시보드, 온라인 검증 벤치마크(라벨링된 27개 질문에서 96.3%, jev-latest에서 중앙값 약 283ms, 2026-09-21). 설계상 정직함: 실제 API만 사용하며 mock 폴백이 없습니다.

Skill that fact-checks a claim against the open web rather than model memory: it splits the claim into independently checkable fact points, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster and accidents, food safety, science, education, sports, entertainment, judicial, and more), searches domestic and international ecosystems in parallel, fetches primary pages, grades sources by type, re-searches with debunking keywords, and reports conclusion-first with a full URL and citation position behind every statement, keeping unverified and undecidable points separate from confirmed ones. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

Live Android device pane next to your DSH conversation: scrcpy-server H.264 streaming (WebCodecs, 30-60 fps), agent tap/swipe/text with auto-screenshot verification, uiautomator element tree with tap coordinates, host-managed recording + logcat debug sessions. FLAG_SECURE pages are detected automatically with a mitigation chain and a tappable text-view fallback. Emulators and USB real phones, human+agent co-operation, session-isolated, loopback-only.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models.

Agent preset plugin for DeepSeek Harness that triages every request, delegates implementation to an expert, and schedules parallel work through a dependency-DAG taskboard and a file-based message bus before an independent review gate. Ships with only 11 core experts out of the box; more expert teams (Agency agents EN/ZH, classic collections) are one-click downloads from the settings page over dual GitHub/CDN channels with sha256 verification.

Group-chat multi-agent orchestration console for DSH: autonomous decision-making, task dispatch, verification and iterative optimization for long tasks; bundles its own backend, installs with `dsh plugin add`.

Stability audit for installed dsh plugins: static risk grading (hook surface, startup work, inject, entry, dep ranges) plus optional isolated install verification.

Provisions the kimi-webbridge bridge daemon (auto-install with SHA-256 verification, auto-start) and registers a 25-action skill that drives the user's real browser through the local bridge.

Experience validation layer for DSH: zero-token collection of tool-failure/retry/search signals, AI refinement into verified skill books (three-layer verification), looked up at task start. Ships 10 trial skills and benchmark data (complex-task success 100% vs 60% bare).

Reliable todo panel that survives restarts (official panel only re-renders on write — fixed via projection pre-warm) with three-state completion verification: evidence exists → verified, fake evidence → blocked, no evidence → unverified badge; settings toggle to fall back to official behavior.

SMS forwarding webhook for DeepSeek Harness. Phone apps (SMS Forwarder, Tasker, or any HTTP POST) push messages to a local HTTP endpoint; the plugin stores them as JSONL and exposes sms_recent / sms_search tools so the agent can read SMS verification codes during tasks. Auto-extracts the first 4-8 digit OTP from each message, supports keyword filtering, and works over LAN or Tailscale.