Plugins

Adds a subagent_routed tool that runs a one-shot subagent fully mounted on any agent preset from any session, with per-call model/provider override and a model-availability pre-check.

Automatic Flash/Pro routing for DeepSeek Harness subagent calls: light tasks run on a cheap model (e.g. V4 Flash), heavy tasks stay on the strong model — with per-call overrides and /delegate session modes.

A global task library plugin for DeepSeek Harness featuring cross-session persistence, a real-time generative-UI browser panel, and subagent job synchronization.DeepSeek Harness 全局任务插件：提供跨会话持久化任务库、生成式 UI (Generative-UI) 悬浮面板及子智能体 (Subagent) 状态自动同步。

A full-screen terminal workbench for DeepSeek Harness with a durable assistant, workspace-grouped project sessions, transcript-only scrolling, and structured thinking, tool, diff, plan, and subagent views.

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.

A model-native meta-agent plugin for DeepSeek Harness: the model synthesizes task-specific workflows at runtime from five agentic workflow patterns (prompt chaining, parallel workers, router, supervisor, evaluation loop) and coordinates tools and subagent

Extends dsh-subagent-tools with a per-call cwd for subagents, shipped with the two in-process provider patches it requires.

Per-call model, provider, persona, and toolFilter overrides for subagent delegation, with @preset: references and provider/model composite ids.

Cross-session task queue with handoff notes: sessions and subagents push, claim, complete and cancel tasks on a shared file-backed queue, and leave a handoff summary for whoever picks up next.

Recovers known invalid explicit model arguments in DSH subagent and subagent_fork calls by removing the full override and retrying once through the original guarded pipeline.

Code can Vibe, progress must be Visible. No guess, less stress. See progress you can assess. Make project progress visible with local algorithms, optional AI assistance, task checklists, and subagent tracking. View overall progress, subagent activity, current operations, and estimated time remaining in a draggable panel. Supports DeepSeek Harness Web and Desktop. Requires Harness ≥0.2.2-rc.1 and Node.js ≥24.9.0. Local estimates require no additional model requests. AI assistance is off by default; enabling it incurs charges from the selected model provider. Probe usage and estimated costs are available in the panel.

Build named subagents and skills in a sidebar panel, then call any subagent by name in a conversation. Each subagent selects a model, reasoning effort, spawn or fork mode, a tool allowlist and skills; skills can be global, per workspace or per conversation.

A DeepSeek Harness (dsh) plugin bundle combining pi-better's codebase-grounded prompt deepening (/better) and subagent brief verification with DSH's Cordis host/web-client architecture.

Session-level root privilege bridge for DeepSeek Harness: ask mode with per-request web approval, full root mode (polkit password entry in the web UI) and fakeroot mode, with sudo or run0 --empower escalation and a configurable subagent sudo policy. It escalates real commands with sudo or run0: in ask mode each request waits for your approval; in full root mode every bash command of the session runs elevated after one password entry in the web UI. Delegated subagents need per-request approval by default (subagentPolicy: request).

Pre-install security gate: quarantines each plugin, skill and subagent bundle with install scripts disabled, scans it with Cisco Skill Scanner, SkillScan, Cisco MCP Scanner, OSV-Scanner, Trivy, Gitleaks and optional SARIF tools or an LLM judge on a DSH model, then passes, asks for review or blocks it. Needs the install-gate hook proposed in deepseek-ai/deepseek-harness#12999.

QQ Bot channel and D&D 5e Dungeon Master plugin for DeepSeek Harness (fork of @tencent-connect/dsh-qqbot; do not enable alongside upstream): /dnd runs turn-based campaigns with 19 `dnd_*` tools for dice, checks, grid positioning, fog and battle maps, story chronicles, snapshot rollbacks and an optional dedicated combat subagent, plus /persona per-chat switching with handoffs, shared Markdown notes, sticker collection, read-only Bilibili tools and per-chat tool-access gating. Direct and group chats default to open in cordis.patch.yml while non-allowlisted QQ chats are blocked from shell and subagents; requires QQBOT_APPID/QQBOT_SECRET or in-app QR binding, with optional sharp for rendered maps and ffmpeg for audio/video. Shared notes are visible to every session, so private-chat content may be recalled in groups.

Plays a chime or a short melody when an agent turn finishes, with five synthesized tones plus a custom audio upload, optional spoken announcement, optional system notification, and per-subagent control; settings are stored on the host.

Ranks models in a ten-slot ladder, routes each subagent by a 1-10 difficulty, and falls back a tier when one fails. Windows only; applies to sessions that opt in. Subagents can also launch local agent CLIs (Codex verified, nine others experimental), and a subagent granted full authority runs its CLI with --dangerously-skip-permissions, --yolo or --force. Run records go to .dsh-supa/ in the workspace.

JetBrains Junie CLI as a one-shot DeepSeek Harness subagent provider over the Agent Client Protocol, with a settings page for model and thinking depth.

One-shot OMP subagent provider for DeepSeek Harness — each delegation spawns the local `omp --print --mode json` CLI running with the user's own ~/.omp configuration and model bindings, and delegations are serialized so a single-session local engine is never oversubscribed. Requires the OMP (oh-my-pi) CLI installed locally and DSH 0.2.2-rc.2.

Adds a Settings page to pin one OpenAI-compatible subagent model (or follow the main model), writes the official subagent-model-selection allowlist, reminds the parent to pass that route, and optionally runs one-shot tasks through an isolated Pi CLI provider.

Per-workspace model packs: bind a named provider, model and reasoning effort plus the four subagent tier routes to a directory. Applies to new sessions in that directory; a session that has not run a turn yet also follows a pack switch, while sessions that already ran a turn are never changed.

Enhanced derivative of ai-shushu/dsh-quota-meter; cannot be installed alongside it (both serve /quota). Per-session spend and quota meter for DSH: bills real token usage against an editable model price table (including peak/off-peak pricing), shows a live progress bar and, in the session header, a balance capsule (the balance needs a DeepSeek API key), and blocks new model calls when a session budget runs out. Subagent and helper-call spending rolls up into the parent session ledger.