플러그인

공식 스토리지 도메인을 통한 DeepSeek Harness용 크로스 세션 메모리: 메모리는 ctx.storage(storageDomain 테이블)를 통해 유지되고 등록된 섹션(memory:recall)을 통해 시스템 프롬프트에 주입되며, memory_save / memory_forget 도구로 에이전트가 자신의 메모리를 읽고 쓰도록 합니다(maxMemories 설정 가능).

DeepSeek Harness용 토큰 어텐션 관리 패널: 작업/일/주/월 단위 토큰 사용량과 비용 추적(입력 히트/미스, 출력, 추론), DeepSeek 피크/오프피크 가격, 작업 유형 인식, 세션 전환·핸드오프 작성·컨텍스트 압축 시점 조언.

사용자 정의 API 모델용 추론 노력 티어 관리자 및 크로스 세션 선호도 메모리: 설정 → 모델 내 인라인 low/medium/high/max 토글, 원자적 설정 쓰기.

DSH 플러그인 설치 보안 게이트의 정적 번들 형태입니다. 페일세이프 정책으로 cordis_define/cordis_run을 검토하며, 검토/감사 도구와 브라우저 승인 팝업(agree / agree+whitelist / reject; agree+whitelist는 플러그인 패밀리를 tru에 기록)을 제공합니다.

DSH Web용 픽셀 아트 추론 노력 슬라이더. 0~100 연속 드래그, 16ms 스로틀 쓰기, 레벨 스냅 커밋, 그리고 슬라이더가 움직일 때 점화되는 WebGL 잉걸불 화염.

DSH용 remove-pdf-background-gray 스킬 등록: 이미지 기반 PDF의 회색/오프화이트 스캔 배경을 흰색으로 바꾸면서 해상도, 페이지 형상 및 앤티앨리어싱된 텍스트 가장자리를 보존하고(무손실 Flate 재기록), 단일 Python 스크립트(pypdf + Pillow + numpy)로 처리.

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

개발 전에 로컬 코드와 GitHub/npm을 조사해 재사용 가능한 구현을 찾고, 재사용과 재작성의 차이를 평가하며, 아키텍처 결합도를 점검한다.

하네스 자체의 기반 위에 있는 워크스페이스별 네이티브 메모리: storage-domain JSON 유닛에 사실과 상한이 있는 상시 프로필을 두고, 쓰기는 승인 게이트와 `(sessionId, seq)` 인용을 거칩니다. 결정론적 회상과 과거 세션에 대한 session-query FTS를 제공하며, 외부 서버나 사용자 지정 SQLite는 필요 없습니다.

세션 헤더에서 에이전트가 작성한 모든 파일을 검토: 파일별 hunk와 변경과 별도로 집계되는 거부된 쓰기.

세션 범위의 Markdown 작성 패드를 대화 옆에 도킹합니다. 편집/미리보기 모드, 선택 기반 AI 다시 쓰기, diff 검토, 실행 취소, 초안 복구 기능을 제공합니다.

증거 우선 운영 키트입니다: 6가지 읽기 전용 도구(기능 카탈로그, 단계별 워크플로 계획, 패키징된 스킬 리더, 범위 제한 로컬 메모리 검색, 저장소 릴리스 감사, 릴리스 체크리스트)와 5가지 패키징된 스킬을 제공하며, 계획과 감사만 수행하고 원격 쓰기는 하지 않습니다.

Claude Code's auto memory in DeepSeek Harness: the index in every request, and tools to write and edit it

Second-model gate on the assistant turn, installed in two parts: copy engine/ into ~/.dsh/plugins/ and mount it by absolute path in the profile patch (the bundle itself only installs the settings panel), then switch off the default dry-run mode that only logs verdicts. Once active, a separate judge call scores the draft against the numbered criteria (0-10 each); any criterion under 6 fails the turn and sends it back for a rewrite, up to 3 rounds by default. The web panel edits criteria and thresholds, and every verdict is appended to an audit log.

The cyber-elixir of youth for the desktop client: fixes the `desktop welcome: Web authentication failed` (HTTP 431) launch failure — an Electron random-port launch lets `dsh-auth-*` login cookies pile up per port (70+ of them, ~229 B each), the startup request headers blow past Node's default 16 KB cap, and the client can no longer launch. Two fixes in one: a scriptable cleaner that removes leftover login cookies from the cookie database (Chromium SQLite) — explicit, offline, keeps a `.bak` copy, `--expired-only` narrows the scope — and a `patch` feature on the settings panel that fixes the launch port through the profile `cordis.patch.yml`, so the client always starts from a single port and cookies stop accumulating across different ones (rewrite `port` as a `!!js` expression to keep the `--port` flag in charge; a per-profile snapshot makes one click revert it). Read the README for usage. Interface, CLI output and market metadata in 9 languages. The purge runs from the bundled CLI (`dsh-cookie-cleaner --clean`) only while the client is fully closed; the in-app half is read-only. npm: `dsh-cookie-cleaner`.

A consent-gated personal profile store: people are indexed by name, entries by person and key, and no profile record is read before the current session is authorised. Sensitive entries come back masked unless the user authorises that tier separately; credential-like values are refused at write time. Ages and next birthdays are computed at read time, so asOf restores the answer for a past date, and facts that rot (height, weight, address) carry freshness warnings. Five profile_* tools plus a settings page to browse, edit, delete and revoke grants.

A memory plugin that forgets on purpose: short-term memories expire after 48h, long-term ones are rescheduled by Ebbinghaus/SM-2 curves and rarely-used ones fall asleep instead of bloating your context. Long-term writes stop in an approval center, so the agent cannot rewrite your persona on its own.

Prompt booster for the composer. Left-click the composer button and the draft is lightly polished and replaced in place (undoable, no popup). Right-click opens a menu with 8 built-in modes plus your own, where each mode's template can be edited or new modes added (saved on the host), and the model used for the rewrite is picked from the live dsh model list. Other modes show a before/after preview. Based on rongxingda/dsh-prompt-enhance (Apache-2.0); do not install both — both add a composer button and share Ctrl+Alt+E, so disable one of them if the upstream is present.

Adds two enhancements to DSH ask_user_question choice cards: right-clicking an option expands a per-option note that is merged into the submitted custom answer, and a footer field asks a side question answered by a fork subagent from the session context, read-only, with no write-back. Keeps left-click, skip, paging and the countdown working as before, and only claims generic choice cards, not plan review or approval cards. Supports DSH 0.2.x from 0.2.0-rc.1 (verified on 0.2.2-rc.1) and Node.js 20+. Derived from buaaflyaway/dsh-question-note (MIT) and inspired by MichengAI/dsh-btw (Apache-2.0); do not install it together with dsh-question-note — both take over the same ask_user_question card.

Optimize prompts in the DeepSeek Harness composer: identify missing requirements, insert a sentence from 90 method cards, or compare and edit a full rewrite before you send.

A sticky-note wall in the DSH sidebar: nine paper colors, categories, search, archive, to-do checklists with stable item ids, and agent read/write tools.

Brings the rtk token-saving setup from Claude Code to DeepSeek Harness: commands rtk can rewrite are rewritten, and builds, tests and logs it cannot reach are compressed; git, cargo, npm and pytest are covered. Compressed output tells the model what was elided and how to recover it; when the sandbox cannot reach the rtk store the original is saved and its path given. Savings show without a command: a pill below the composer, with `/rtk stats` for detail. When a rewrite is unreliable the original command runs as usual: if rtk cannot run, or the returned command would drop arguments, nothing breaks. The rtk binary ships with the package, so mainstream platforms need no separate rtk install, unlike most other rtk plugins.

Qoder-style workspace mode and branch chips on the session row; picking a branch arms it, and the first message creates a dedicated git worktree and moves the session into it. Windows only: the write grant runs PowerShell Set-Acl; elsewhere Worktree mode reports an error and stays in the main checkout.

Multi-round deep research in the DSH sidebar: each round fans sub-questions out to parallel sub-agents, then continues from where the last round stopped and writes a cited report.