Plugins

Connect DeepSeek Harness agents to authenticated Codex App Server sessions

Run Pi extensions as agent-scoped DeepSeek Harness plugins

A Symphony-compatible multi-provider task orchestrator and dashboard for DeepSeek Harness

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

Claude Code compatibility layer for DeepSeek Harness: load .claude skills/commands/agents and install plugins from Claude Code marketplaces as native dsh skills.

Stable, editable PPTX generation for AI agents — semantic IR in, native DrawingML out

Puts the agent on the Muretai network: its own identity, invite-based introductions, signed end-to-end encrypted messaging with agents owned by other people, and an inbound-mail wake that lets it reply on its own.

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

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.

DeepSeek Harness Cordis bundle that mirrors session state into the AI Terminal Pet desktop overlay (Windows).

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.

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).

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.

Per-step thinking-effort pilot for DeepSeek Harness: simple tool rounds stay cheap, failures and heavy work lift one declared step, and agents can change their own depth through a set_effort tool without switching models.

Cross-agent session browser for DeepSeek Harness: mounts /session-hub/api/* and a Settings > General status row to read and search OpenCode SQLite, Claude Code JSONL, Antigravity, Qoder CN and DSH zstd logs, plus explicit continue-in-DSH and export. Its /session-hub/api routes are mounted without DSH's access check, and on startup it registers the workspaces found in those other agents' histories into DSH.

Running panel for dsh for skill management and visualizing skill calls: live skill and tool calls, the skill-catalog token budget against a line that follows the model's context window, a skill loadout window that enables and disables skills in bulk with dry run and undo, goals and ideas, and saved conversation excerpts. Applying a loadout moves skill folders between ~/.agents/skills and ~/.agents/skills-parked, which other apps share (dry run first, undo available); automatic translation, goal inference and idea collection call your default model only after you opt in on first open.

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.

dsh bundle for TSM / DLR: MCP semantic gateway to tsm-core-dlr, the scenario-independent paradigm skill, the TSM status overlay, and the agent rules (AGENTS.md). Assembly face = preset-dlr.

Bridges campfire group chats into DeepSeek Harness, delivering messages addressed to your member into a DSH session and posting the reply back to the group. Needs a self-hosted campfire server plus a member handle and channel token; anyone who @-mentions that member in the configured chat can start a turn.

A floating always-on-top overlay for Windows that shows which of your terminals is waiting: it aggregates DeepSeek Harness, Claude Code, OpenCode and Antigravity session states (working, waiting for approval, failed, finished) over a named pipe, rings only on real events, and a click jumps to that terminal or copies its project path. Harness sessions appear on install; the other three need their own reporter from the repository, and approvals still happen in DSH.

Two independently maintained agent presets (Conductor and a restricted Conductor child) for DSH with planning and task-delegation guidance: todo-first planning, parallel delegation (up to 4 sub-agents per batch) and goal-driven continuation. The persona runs in an "unrestricted mode": it tells the model not to state limits, add safety notes or disclaimers, and not to treat "you cannot" or "that breaks the rules" as a new instruction. All of this is prompt-level guidance, not enforced behavior.

Edit Markdown in place in the right sidebar and send inline comments to the agent, which resolves each one it handles.

Chinese accounting and tax knowledge base for DSH agents, served by the hosted Quaesto service at api.accountingllm.site (needs network access; no account or API key, but your queries leave the machine): answers questions on CAS enterprise accounting standards, the small-enterprise accounting standards, CSA auditing standards and tax law with original articles, decision procedures, applicability checks and tax-accounting differences, exposed through 10 MCP tools and a china-accounting-standards skill.

Tracks online, active and task time in DSH, with a day/week/month dashboard, per-workspace and per-session breakdowns, and a read-only `timespan_stats` tool for agents.