플러그인
DeepSeek-Harness 플러그인을 찾아보고, 필터링하고, 설치하세요.
플러그인 150개 찾음
dsh-db-tool-ru
steelunicorn/dsh-db-tool-ru
A fork of mengqi1436/dsh-db-tool with a Russian interface and English server messages, per-grant database allowlists that open only the databases you tick, and export_to_file / execute_file actions that move query results and statements between the project folder and the database byte for byte. Replaces the original plugin; the tool name and the shared data directory (Documents/DSH/db-tool) are the same, so do not install both together.
dsh-plugin-sandbox-mode
wth373737/dsh-plugin-sandbox-mode
A separate agent mode for DeepSeek Harness: reasoning goes into a sandbox document, every action is written there first and then executed by reading it back, and the final answer is printed from that document. Direct tool calls are blocked per preset, and the output also lands as a file card. Deliberately more expensive, and the mode picker says so.
dsh-ruleset
cengcengcai-creator/dsh-ruleset
Audit whether an agent actually follows your AGENTS.md-style rules: 15 predicates evaluated over native DSH events, a pre-execute approval gate for red lines, per-finding false-positive triage, and baseline significance so a noisy day does not read as a regression.
dsh-connect-codearts
hxgh776/dsh-connect-codearts
Connects a locally signed-in Huawei Cloud CodeArts Agent account to DeepSeek Harness: chat models whose tool calls are executed locally by DSH, a read-only token-usage view, and an opt-in daily check-in engine that stays closed until a read-only welfare probe verifies. Reads the CodeArts CLI auth file only (never copies, refreshes or writes it); Windows x64; doctor and probe CLIs included. Registers the codearts provider, so do not install it alongside another CodeArts plugin.
dsh-codex-bridge
danceelephant/dsh-codex-bridge
Moves the skills already installed in Codex into DeepSeek Harness with one command — the bridge between the two. After installing, DSH can scan, inspect and import those skills directly: imported skills appear in the DSH skill list and are loaded on demand by the model like native skills. Imported descriptions are compressed to fit the DSH prompt budget (220 characters by default), upstream changes and removals can be checked with one command, and any import can be removed cleanly. It never executes imported code: scripts are only listed, bodies are only read and registered. Six tools plus a CLI, zero runtime dependencies, no build step, Node.js 20 or newer.
dsh-plugin-voice-alert
venompool888/dsh-plugin-voice-alert
Spoken alerts on macOS that name the source and project: announces approval requests automatically and adds a voice-alert skill the agent uses for verification codes, finished long tasks or when it is stuck. DeepSeek TTS via an API key (DeepSeek official, a third-party base URL, or the key already set in DSH Models), tested before saving and falling back to the macOS system voice; speaks only after 30 seconds without keyboard or mouse input and repeats until you return, with AI-written lines in a chosen tone (professional, tsundere, cute, clingy, cold or custom); a Settings → Voice page with instant previews, speech speed, 10 spoken languages and an away mode.
dsh-connect-loomy
hxgh776/dsh-connect-loomy
Connects the locally signed-in Loomy (iFlytek) desktop account to DeepSeek Harness: chat models with reasoning and tool calls executed locally by DSH, plus a read-only credits dashboard (total balance, daily allowance, available balance). Reuses the Loomy app's own session file without copying or storing credentials; doctor and probe CLIs included. Windows x64.
dsh-autopilot-harness
adamsshen/dsh-autopilot-harness
Adds a plan-then-execute loop to DSH: /autopilot-on runs grill rounds and writes brief, plan and checklist files, /autopilot-run works the checklist item by item, and after a product-code edit the plugin intercepts the turn boundary and steers the agent through rotating self-review rounds before advancing.
dsh-slowmist-security-guard
wjl906/dsh-slowmist-security-guard
Security guard for DeepSeek Harness (Cordis): reviews every tool call in pre-execute against SlowMist agent-security rules, denying or flagging risky commands, MCP servers and skill loads, external URLs and repositories, untrusted documents, and EVM or Solana addresses; scans tool results for prompt injection after execution and ships a slowmist_scan audit tool plus an injected security policy prompt. Rules follow the open-source SlowMist Agent Security Skill (MIT).
dsh-steward
stallenlu/dsh-steward
Read-only diagnostics for a DSH install — boot-crash logs and the cause named in them, config drift against a recorded fingerprint, backup freshness, workspace growth, plugin updates, host-version compatibility, duplicate client ids, and model availability — plus an action layer that always shows a plan first and needs a single-use fingerprint and explicit confirmation before anything is written. A checkup also runs 45 seconds after every host start; when the 3-hour probe cache is stale it sends a one-line test prompt to the default model and a few models of each configured provider (model.probeOnReport can switch this off). Registers the agent tools dsh_steward_report and dsh_steward_act (clean caches via dsh-disk-cleaner, backup via dsh-config-manager, disable or enable a bundle, set the default model; execute takes the plan's hash plus confirm: true) and a system-prompt section telling the agent to run the report first when something crashed.
dsh-model-radar
chip-g0202/dsh-model-radar
Runs a four-task, 150-point model intelligence benchmark inside DeepSeek Harness (Qin 60, Pompeii 45, Pelican 22.5, Candy 22.5): each selected model × reasoning-effort pair executes every task in its own isolated subagent session, Qin and Pelican are graded by the selected judge model against rubrics, Pompeii and Candy programmatically, and batches keep scores, artifacts and cost. Adds a 0–1000 real-world performance score per model × effort computed from local session logs across seven dimensions (output speed, first-token latency, reasoning speed, tool cadence, tool latency, tool success rate, cache hit), with baseline deltas and controlled speed runs, plus a sidebar page with ranking, performance, history and settings views. Each batch spends real tokens of the candidate and judge models, and candidate subagents get file and bash tools inside an isolated run directory.
dsh-ps-preflight
dingchenhui0618-arch/dsh-ps-preflight
Grades every PowerShell command an agent is about to run before it runs: deletion, overwrite, network download and credential access are four required classes, plus dynamic execution, system and privilege changes. Verdicts are a pure deterministic rule function — no model call, no network, sub-millisecond — with two escalation rules (download+execute, credential+exfiltrate) that jump straight to high. High risk stops the tool call for a second confirmation (in-panel queue or the native approval), deny or timeout means it never runs; medium is logged but never blocked. Every command and its verdict, including the redacted command text, is appended to a local JSONL audit log. Quoted danger strings are treated as data, -WhatIf is respected, -EncodedCommand is decoded and analysed again. Host + client halves, zero runtime dependencies, 55 rules, 136 tests.
dsh-codex-claude-pipeline
lidaqi001/dsh-codex-claude-pipeline
A DeepSeek Harness agent preset where a Codex subagent analyses and decomposes the task, Claude Code subagents execute each work item, and the session only dispatches, checks and reports. Requires Codex installed and signed in locally, and Claude Code signed in locally.
subagent-orchestrator-dsh
turambarr/subagent-orchestrator-dsh
Experiment-orchestration SOP skill for long-running experiments. A top-level model drafts a decomposition plan — subtasks, the model for each, an acceptance figure with tolerance, and dependency order — and dispatches only after the user confirms that plan; each subtask then goes to a lightweight executor subagent as a self-contained prompt, and its report is confined to measured facts and the delta from the agreed figure, with judgement and decisions staying at the top level. Ships one plan template and five task templates (gather, execute, consistency check, read-only review, mechanical transform), acceptance gates split into a task layer and an experiment layer, and three rules that stop internal-consistency evidence from being presented as independent or external validation.
dsh-plugin-penpot
sdf123098/dsh-plugin-penpot
Connects Penpot to DSH across two independent channels with 9 tools: 5 MCP tools (execute_code, high_level_overview, api_info, export_shape, import_image), 2 browser-free REST tools (penpot_read and penpot_write to create files, pages and shapes or edit attributes without an open tab), plus penpot_status and penpot_control; supports official SaaS, local and self-hosted endpoints with auto-detection and config migration from DSH, Codex, Claude, Cursor, Gemini and .mcp.json, an isolated Chromium launcher, and a five-tab control panel.
dsh-fishgirl-notify
newpage1/dsh-fishgirl-notify
DSH finish reminder: a cute fish-girl pops up “Done!” on your phone via Feishu, ntfy or Web Push, and plays an animated popup inside the DSH page.
dsh-warden
daphne999/dsh-warden
Security review for DSH plugins: reads the manifest, install hooks, native dependencies and source for network egress, dangerous APIs and credential paths, cross-checks the curated market registry, and returns a 100-point verdict with itemised findings. Read-only — it never executes the audited code.
dsh-flow-queue
eclipse-notfound/dsh-flow-queue
Right-sidebar flow editor for prompts, model switches, commands, condition branches and loops, executed only at turn boundaries so an in-flight request keeps its model.
dsh-fusion-lean (fusion-lean)
aliang-code/dsh-fusion-lean
Fusion 360 for DSH: bridges the MCP server Fusion ships (read, execute, update, electronics) with every upstream schema kept byte-for-byte while the always-on tool surface drops 70 percent, adds an editable endpoint under Settings, and wraps a local hf.py modelling loop as nine hf_* tools (needs Python 3.10+ and a fusion-harness workspace).
dsh-staging-guard
mdl233/dsh-staging-guard
사전 실행 훅으로 보호된 root의 읽기 전용 result zone 아래에 쓰는 경우만 거부합니다. 그 밖의 모든 경로는 통과시킵니다.
dsh-work-review
wang-chuming/dsh-work-review
Obsidian 스타일 볼트를 위한 작업 검토 루프입니다. 날짜별 Dream과 번호가 매겨진 T/G 계획을 작성하고 routine으로 표시된 항목만 실행합니다(기본 읽기 전용, --live일 때만 로컬 commit). 7일을 ISO 주간 routine으로 묶고 모든 날짜와 주간 기록을 읽기 전용 사이드바 패널에 표시합니다.
dsh-pen-dev
maxlee/dsh-pen-dev
pen.dev 데스크톱 앱의 MCP 서버를 DSH 세션에 연결해 모델이 Pen에서 열려 있는 `.pen` 문서를 읽고 편집하게 합니다. `get_app_state`, `read_skill`, `execute`, `get_style`, browser 도구를 사용합니다. 일반 설치 경로를 탐색해 서버 바이너리를 찾고, pen.dev 요금제 제한 오류를 짧은 영/중 알림으로 바꾸는 listener와 pen-dev skill도 추가합니다. 비공식이며 pen.dev 바이너리는 포함하지 않습니다.
dsh-change-impact
duyanta123/dsh-change-impact
코드 변경을 근거가 포함된 영향 및 검증 계획(CHANGE-IMPACT.md + change-impact.json)으로 변환합니다. 영향 모듈, 진입점/공개 export, 요인과 신뢰도가 포함된 위험도, 권장 검증 명령을 제시합니다(읽기 전용이며 저장소 명령을 실행하지 않음). 실행하는 것은 Git 읽기 쿼리 rev-parse/diff/status뿐이며 제안 검증 명령도 실행하지 않습니다.
dsh-rtk-bridge
b1inkie/dsh-rtk-bridge
pwsh 및 bash 도구 명령을 rtk rewrite로 변환해 간결한 동등 명령을 실행합니다. rtk가 없거나 동등 명령이 없으면 원래 명령으로 대체합니다. 체크섬 검증 `/rtk install` 다운로더를 포함합니다.