Find the right DSH plugin
for your next workflow

Native conversational image generation for DeepSeek Harness: ask the agent to create an image, and it handles generation and keeps the result directly in the conversation.

One-click launcher for DeepSeek Harness: detects whether the backend is running, starts dsh web if needed, waits until ready, then opens the main page in a new Chrome window. Ships a cross-platform CLI (dsh-launcher start / open / status / make-shortcut) and the harness_launch agent tool.

Local SQLite taskboard as a native overlay page: projects, tasks, comments, relations, attachments and workflow automation, with backlog → todo → in_progress → in_review → done statuses, `taskboard_*` Agent tools that can only submit work to in_review, a headless JSON CLI and a packaged skill.

Auto-resumes dsh sessions whose turn was left mid-flight by a web process restart or by a transient upstream failure, by injecting a 「继续（自动）」 ("continue (auto)") user message so the agent picks up exactly where it stopped — no manual click, no lost context. Triggering scenarios: (1) Upstream rate-limiting / overload — HTTP 429 with code RATE_LIMIT / rate_limit_exceeded / too_many_requests, or type=service_unavailable, or message containing "currently overloaded" / "please try again later" / "all endpoints are currently overloaded" / 5xx. (2) Upstream network / server faults — code SERVER / TIMEOUT / TRANSPORT / EMPTY_RESPONSE, or message matching NETWORK_FAILURE_PATTERN (upstream error / internal server error / service temporarily unavailable / timed out / fetch failed / ECONNRESET / ECONNREFUSED / ETIMEDOUT / socket hang up / network error / connection refused|reset|closed); supports DSH/OpenAI-style error envelopes {error: {code, type, message}}. (3) DSH web restart / crash leaving a turn mid-state — open turn/step without a matching end, pending tool/call without tool/result, or turn/end reason = interrupted. (4) Account-level billing / quota failures (v0.0.11+) — HTTP 402 with code QUOTA / insufficient_balance / payment_required, or message containing "insufficient balance" / "payment required" / "quota exceeded" / "quota exhausted" / "402" — recoverable by topping up the account or switching provider; same dead-loop guard as the other transient classes (no progress after a "continue" → settled, hands control back to the user). Skipped (avoid false positives / loops): assistant/message last, or turn/end reason=completed; cancelled, or non-network / non-billing errors (config / model errors like UNKNOWN_MODEL / MISSING_CREDENTIAL / NO_ADAPTER); dead-loop guard — if the previous "continue" injection produced no content or tool calls and the same error recurs (e.g. some stealth models returning empty under sustained overload, or a top-up that never landed), the plugin falls back to settled and hands the session back to the user. Guardian: 24h scan window + permanent liveWatch (bootGraceMs default Infinity). Set targetSessionId to watch a single session (legacy mode).

One-click prompt polisher for the DSH composer: a ✨ button next to the message box opens a side-chat where an agent refines your rough draft over multiple turns, then you copy the result back. Replays the session prefix to hit the prompt cache, with a full → partial → none fallback for oversized or non-live sessions, per-call JSONL tracing, and a trust fence plus CAS write-back that refuses to overwrite a draft changed since the request. Requires omdsh-dev/DSH-better-sidebar (>=0.16.1); errors explicitly if it is missing rather than failing silently.

Capture selected DSH, local MCP, or native WebMCP calls as reviewed, parameterized routines, expose typed tools, and replay with fresh approval.

Jimu (积木): domain-based orchestration plugin for DeepSeek Harness — domain_plan confirmation, per-domain sub-agents with hand-off, and automatic LLM audit.

Host-side unattended job scheduler: runs one-shot agent tasks or shell commands on cron, interval, or one-time schedules, with persisted at-most-once dispatch state, overlap/misfire policies, and bounded run history.

Minimal prompt x Web PTC capabilities: one-line persona, run_code SDK, subagents, Ralph, web search/fetch, and Windows Git Bash; the general-purpose workflow tool stays hidden.

All-in-one combo patch for STARDUSTLC's 18 DSH plugins: one command injects shared default configs across office, media, DevOps and notification presets; each component installs directly via a one-line add command (flat design, no git subdependencies).

Agent preset bundle for wish and task management: create wishes or tasks from conversation, opportunity-day check-ins, micro-actions, plus a memory store and progress charts in the web UI.

Per-workspace project kanban board: nine kanban_* model tools for agent-driven planning plus a browser board UI, with disk persistence, undo, templates, and archiving.

Runs work as a crew of role agents: a product manager writes the PRD or DoD, waits for your confirmation, then starts architect, engineer, QA and reviewers whose tool sets are locked per role, and shares work through files on disk.

Installs an Orchestrator agent preset that plans and dispatches to model-pinned specialist subagents (explorer, oracle, librarian, designer, fixer, council), with named model profiles switched via an omoslim CLI and a Web inspector button showing the current subagent models.

Agent-driven kanban board: one board per workspace, per-task agent sessions, and a guarded human/agent workflow (Backlog → To Do → In Progress → Review → Done).

Evidence-first self-evolution controller: bounded Cordis candidate generation, one-shot real-Loader admission, Harbor evaluation, and a crash-resumable journaled lineage.

Scheduled coding runs in fresh agent sessions with auditable history.

Plan review with anchored annotations and structured feedback back to the agent.

"Single-Core Writing" plugin for DeepSeek Harness: Thoroughly tool-streamlined and output-hardened for quantized small models, suitable for running long-novel pipelines locally with on-device models.

TongFlow film-crew studio for image, voice, music and video production: the agent writes per-asset TongFlow workflow files (.tongflow.json) that run through TongFlow plugins, with an embedded workflow canvas, a shot/character/take project layout and a manga-drama template; sessions starting with @tongflow open the Studio view.

Persistent multi-model squads configured in Settings and selected in the Composer, with per-member model/tool policies; the main Agent dynamically plans each send as a bounded DAG with bounded reviewer/repair loops, while Run Center tracks retries and per-member tokens from official Harness usage events.

Claude-Code-style lifecycle hooks: configured shell commands run before/after model tool calls with a JSON payload on stdin; a non-zero pre-tool exit blocks the call.

Full local-first issue board embedded in the DSH web GUI: Kanban / list / Gantt / workflow / dashboard views, AI chat per task, attachments and labels, auto-claim of todo tasks driven by dsh-routines — data lives in local SQLite (dsh plugin add @ttmouse/dsh-taskboard).

Scheduled DeepSeek Harness Agent tasks with mandatory end-to-end tests, run history, and bidirectional delivery through nine messaging channels.