Plugins

DeepSeek Harness (dsh) approval answerer backed by the agent-governance sidecar — every approval/request is decided by the deny-by-default gate, L0–L4 rules and the organizational audit chain.

Run Claude Code and Codex as live terminal panes beside dsh: a split view in the web UI, buttons to seat them, and tools that let the dsh agent hand them work and read their screens.

A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.

Discover and verify portable RoleHub roles, pin each exact bundle, then launch its prompt and bundled skills in an isolated, continuable DSH Session with Host-approved tool bindings and optional Agent Team Room attachment.

Hand off focused context without waiting for or interrupting the active Agent: freeze a bounded Session snapshot, summarize it asynchronously with an isolated no-tool LLM, and deliver a provenance-bearing capsule to another Session or an authorized Room—quiet by default for Sessions, with explicit wakeup available.

Same-runtime cross-Session discovery and communication for DeepSeek Harness

Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.

Multi-agent orchestration controller for DSH — tiers, staged receipts, a token ledger and a run panel on top of the official Agent Teams. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

Multi-agent orchestration hub: bridges six foreign agent runtimes (Codex, Claude Code, OMP, Pi, Hermes, Antigravity) into the DSH Web UI — roster, session create/prompt/resume, exec/PTY/task/file lanes, local or cross-machine over SSH/Docker/Incus/Hub. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

An audit workspace for DeepSeek Harness: a multi-agent consultation venue where each review seat is filled by an agent, every judgment is routed to a named review face, and the whole run is kept as a traceable record. Works out of the box: the service endpoint is built in, a workspace is provisioned automatically on first launch, and review scenes come with their seats and agents listed. The built-in service endpoint is the author's hosted server (agent.ak2029.com/kai-pu): scenes, runs and review records are stored there unless you override baseUrl in the profile config.

Multi-workspace agent federation with persistent ticket trees, parallel worker sessions, structured evidence reports, independent acceptance checks, retry/stop and restart recovery. Workers get shell and file tools in the ticket's directory, company_verify re-runs the ticket's acceptance commands in a shell on the host, and scope lists are task authorization rather than a sandbox. State is stored in ~/.dsh/ai-company; the optional company_repo_* tools run separately installed aoci/codegraph commands on any path they are given.

A draggable task progress panel with local estimates, independent teammate progress, optional AI observations, and probe cost diagnostics. Release candidate for the Web profile only; needs Node 24.9 or later and Harness >=0.2.2-rc.1, tested on 0.2.2-rc.2. AI observations are off by default and, once enabled, spend tokens of the session's provider. It uses the same package name and mount id (dsh-task-progress) as chen8923/dsh-task-progress, so install only one of them.

DevLead mode for DeepSeek Harness: a human-only switch turns one ordinary session into a lead with eight devlead_* tools to register workspaces and create, read, continue and watch other ordinary sessions; it dispatches work to those sessions, reviews the delivery and reports, is woken through a durable notification digest when a watched session's turn settles, and can give a dispatched writing session its own Git worktree when the host provides the experimental worktree service.

Session bus for DSH: independent sessions in one project message each other by session id or registered name and wake the target, with a sidebar inbox, unread badges, a roster verification tool, and a per-project switch that stays off until .dsh-bus.json opts in.

3D office view for DeepSeek Harness: the sidebar panel turns the real main session, its sub-agents, tool activity and reports into animated desks, with per-desk screen details and a notification centre for collaboration events; sessions are picked per working directory. Read-only: it starts no tasks, calls no model, needs no API key, and ships its own scene and models (no CDN). Requires DSH 0.2.2-rc.1 (or a later 0.2.x) and Node ^22.19.0 || >=24.0.0.

Control tower tools: dispatch a task to a role agent, read its report, verify and accept or send it back. Requires the separate agent-control-tower Python CLI (tower; it is not on PyPI — install it with pip install -e from the same repo) on the DSH process's PATH plus a tower init-ed workspace; without it every tool call fails with ENOENT.

Adds lasting bots with their own name, photo, persona, memory, voice and model, a Bots panel in the sidebar, and a hidden helper subagent per bot that follows the conversation, searches ahead and leaves notes the bot reads; voice uses your own ElevenLabs, OpenAI, Groq, Mistral or Deepgram key. Interface and prompts in Brazilian Portuguese.

Project spaces, group chats, task boards, memory and usage for teams of DSH bots

Five-tier reasoning protocol injected into the system prompt — off / light / standard / deep / multi-agent, 0 / 3 / 9 / 17 / 19 rules — with the tokens each tier adds per request shown beside it. Alongside it: a claim ledger that marks a load-bearing claim with no evidence or check as unsupported, read-only analyst briefs, JSON-declared custom tools that work in the same turn, one persistent PowerShell session, and re-injection of host context after a configurable message gap. Tier 0 injects nothing and mounts no tools. A derivative of husongan/dsh-deepseek-2027 (MIT); do not install both — each injects its own reasoning-protocol section into the system prompt.

Plan-native multi-agent workflow for DeepSeek Harness: plan directs, work coordinates, code writes, and review audits read-only. Ordinary tasks need no authorization card or budget form. Includes 14 chain_* tools for explicitly authorized controlled rounds, with a frozen T0 baseline, layered evidence, and blocking close gates. Provides per-role model settings. Requires the sibling l1-presets bundle. For new installs, Weihao654/dsh-workflow#role-chain provides this runtime and the four presets in a single bundle. Do not enable role-chain alongside either legacy l1-presets or l2-protocol.

An Orchestrate tab in dsh-better-sidebar and 14 orch_* tools to spawn, prompt, fork and cancel agent chats, run command, scrape, http and agent tasks on local, ssh or remote runners, show provider status cards, and serve a secret-protected machine API. Requires DSH >= 0.1.1-rc.1, Node >= 22.5, the web profile and dsh-better-sidebar.

Skill bundle for tiered multi-agent science campaigns in math, physics, astronomy, engineering, and biomedical evidence: a shared blackboard, independent verifier and red team, wolf-pack and flanking tactics, token and time budgets, known-answer evals, a four-agent pendulum pilot, and a six-agent fourth-order pilot that caught and corrected a benchmark answer-key error. Does not claim open-problem solutions.

DeepSeek Harness 局域网中继插件：一台机器在 DSH 进程内做 hub，其余机器粘贴加入码即可加入；跨机器 Agent 消息互通、离线补投、自动唤醒会话，标准 DSH bundle，装完即用。

Two DSH delegation presets — a fixed 8-seat crew, or up to 3 day-rate temps by convention — with call-time guards that refuse the other shape's delegation tools. The 8-seat preset additionally needs @deepseek-ai/dsh-experimental-agent-team-profile in the profile's dsh.profile.bundles; without it that preset has no team tools and degrades to solo work.