플러그인

Evidence-first frontend release checks: real-browser content, accessibility, runtime, network, and baseline regression reports with screenshots.

Read-only repository fact scanner kernel for DSH analysis plugins: deterministic probe / file index / modules / dependencies / entry points / symbols / graphs and git facts over a stable JSON schema (CLI + library + skill runbook).

Replaces the headless startup to add --model provider/model, --resume <id|latest>, --continue and --session-info flags to dsh headless runs.

Quality suite: background tsc --noEmit diagnostics fed back after the agent edits TypeScript, plus a /code-review command running five parallel review lenses with confidence scoring; absorbs dsh-code-check and dsh-command-code-review.

Live session status on the browser tab favicon with sound notifications for pending input and completed tasks.

Task-complete and question notification sounds for the DeepSeek Harness Web UI: a soft chime when the agent finishes a turn, a ding-dong when it asks you something (questions, plan reviews, approvals). Synthesized Web Audio, zero assets, mute toggle and volume slider in the session header and settings.

Maintains reusable named subagent profiles for DeepSeek Harness and runs them with per-profile model, reasoning effort, and agent-preset settings.

Task Runner mode for DeepSeek Harness: the main agent decomposes large tasks into independent subtasks, dispatches them to subagents (default local model) in fresh short contexts, and synthesizes results; concurrency and worker/orchestrator models are configurable in the settings panel.

Turns a product or UI request into an implementation-ready design spec with /ui-workflow and /ui-rerun. Analysts run through a read-only ui_analyst tool, and the lead agent writes docs/ui-workflow reports.

Intercepts turn-stopping to force one critique-and-improve round after each completed turn before the agent stops.

Multi-agent isolated debate for DeepSeek Harness: debaters of different temperaments research independently (no herding), then cross-examine, then judges converge to a conclusion. Runs as a background job with per-agent progress, token accounting, wave-parallel execution, and session-referenced resume.

Captures every plan the agent presents through exit_plan_mode as markdown under <workspace>/.dsh/plans, opens a review window, and keeps a Plans history tab recording the outcome of each plan.

Preset workflow template library: 12 reusable orchestration script templates with wf_template_list / wf_template_search / wf_template_run / wf_template_validate tools and static template validation.

Input redundancy pruning for DeepSeek Harness — drop repeated/redundant tokens before they reach the model (layer ②).

Google's Agent Skills (google/skills) for DeepSeek Harness: 128 bundled SKILL.md skills for Google Cloud, BigQuery, GKE, Gemini, Firebase, ads and analytics.

Resolves unique kebab-case skill substrings in slash tokens, so /oneshot can load game-package-oneshot.

Product-thinking companion for DeepSeek Harness: clarifies negative boundaries first, separates facts from assumptions, routes through seven product lenses, and persists confirmed decisions to project memory.

Converts half-width punctuation in AI replies to full-width Chinese punctuation, so copied answers stay publication-ready.

Resident-index grep for DeepSeek Harness that shadows the built-in grep/glob tools under the same names: repeated content searches hit an in-memory index ranked by access/modification frecency, and glob serves the built-in ripgrep semantics when available, falling back to the index otherwise.

Control, organize, diagnose, design, personalize, and answer product knowledge questions for a Yeelight smart home, powered by the local yeelight-home runtime.

채팅에서 캔버스로, 그리고 작품으로 — ComfyUI를 DSH 안의 비주얼 워크플로 IDE로 구동. ComfyUI(로컬 또는 클라우드)를 DeepSeek Harness Web에 분할 화면 캔버스로 내장하고, 에이전트가 채팅에서 쓴 프롬프트와 스크립트를 눈앞의 캔버스에 실시간 적용해 이미지·음악·영상·3D를 생성합니다. 캔버스 작업(파이프라인 구성, 워크플로 읽기/쓰기, 노드 편집, 연결, 실행, 매개변수 조정, 디버깅), 프로덕션 작업(batch_run 일괄 매개변수 스윕, get_outputs로 출력을 채팅으로 자동 회수), 환경 관리(ComfyUI 원클릭 실행, 코어와 모든 커스텀 노드 일괄 업그레이드). 본 패키지는 DSH 측 플러그인이며 ComfyUI 측 브리지 노드도 함께 제공합니다.

A @-file reference tool for DSH: registers an at_file_read tool that injects workspace-file contents into the session, with traversal protection and a 50KB truncation cap (MIT).

Folds the tool-definition prompt surface when many MCP servers are installed: a static KV-cache-stable catalog plus BM25/bge-m3 hybrid tools_search and batch tools_schema expansion, so hundreds of tools stay discoverable without spending their full schemas every turn.

Monitor DSH session status, track session runtime information and support file preview.