Plugins

An F1 Race Control theme for DSH Web with four switchable team skins, broadcast-photo backgrounds, light and dark modes, and native appearance controls.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).

Lets the AI insert streaming-generated UI into the conversation or a side panel, written in TSX — already one of the model's native languages, so there is no JSON schema to teach it. Rendered without flicker, state kept across frames with no hard remount, and a click in the card driving the next chat turn. Inline is where streaming matters most; the side Canvas is the more agentic shape. Cards get agentic capabilities of their own — run bash, curl, call the model, read and write files.

TickTick (滴答清单) daily task dispatcher: an interval timer pulls due tasks from a chosen list into a Markdown task file and notifies only when the task set changes (WeChat via ClawBot / flomo / macOS); it can also auto-execute each task in its own headless DSH session under a configurable timeout, optionally gated to DeepSeek's off-peak hours so peak-time work queues to the next off-peak window instead of starting, plus a settings panel for the deferred write-back queue and dispatcher_status / dispatcher_config / dispatcher_run / dispatcher_report tools.

Turns code review into a hard gate: deterministic severity rules, LLM-assisted findings, a team approval quorum and a durable compliance audit trail that must pass before a merge proceeds.

SOP-driven business Agent Teams for DeepSeek Harness: configurable captain/member agents, human- or agent-defined SOP workflows (nodes, dependencies, quality gates, manual gates), event-driven task scheduling, and a web dashboard (SOP canvas, run board, a

Un-clamps the composer stats footer: long turn and token stats lines span the full composer width instead of truncating with an ellipsis.

Named user credentials the model uses by reference: values are entered on a Settings → Credentials page and injected into each shell execution as DSH_CM_* variables instead of being printed into the transcript, with credential_read as the documented last resort.

Installs the coaligne-workflow skill for CoAligne team collaboration; requires CoAligne Desktop (signed in) to provide the MCP connection - not usable without Desktop.

OpenSpec 流程的 Agent Team：面向实施阶段的多 Agent 工作流编排。

Reloads an upgraded plugin inside the running dsh process instead of restarting it, and rolls back to the old version when a reload fails.

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.

Deep-collaboration writing agent for DSH: per-user writing-style learning from edit pairs, clarify→outline→section-writing→red-team→reader-gallery flow, project-to-report synthesis (lab report / product intro / survey / README), 41 MCP tools, and web selection-improve UI with in-app file preview.

A `search` tool that learns to pick between fast and thorough search strategies using a contextual bandit (Thompson sampling), improving from real usage instead of a fixed heuristic.

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.

dsh plugin: unattended approval gate — subagent/scheduled/cron approval requests get a bounded answer window, then settle with a fail-closed default instead of hanging forever (per origin or per session)

Unified @ mentions in the DeepSeek Harness web composer: five built-in categories (file, folder, skill, past chat, plugin) plus a data-source seam any plugin can register through, references to absolute paths outside the workspace, and a candidate menu that can be scoped by a folder named earlier in the draft and pages with PageUp/PageDown instead of hiding rows.

DeepSeek Harness plugin that asks which provider and model should run each delegation before the child starts, so a subagent can go to a cheap or local route instead of the parent's.

Adds a button beside the composer and a global hotkey palette (default mod+shift+k) that hand one-off questions to a web chat instead of into the harness context: the draft is lifted out of the composer, copied to the clipboard and opened in the templated URL. Ships target-site presets (DeepSeek, Kimi, Qwen, 豆包, 腾讯元宝, GLM, Gemini), a local question history that can be re-opened, copied, or inserted back into the composer, and a settings tab for site, URL template, hotkey, clipboard and history.

Routes eight DSH lifecycle events through dedup, quiet hours and digest batching into seven channels. Severity maps to the fields Bark, ntfy, Telegram and webhooks actually support; failed deliveries retry with jittered backoff and survive a restart; per-channel circuit breakers stop hammering a dead endpoint; and a self-check reports a degraded relay instead of going silent.

Nushell-only shell executor, dialect preflight, and Nushell syntax teaching for DeepSeek Harness (dsh 0.1.7-rc.1): every ctx.shell execution runs as `nu --no-config-file -c`, other shells are refused, bash/PowerShell habits are refused before they spawn (

Ops request channel for a team over Feishu DMs — a colleague's message waits in a serial queue behind an approval card that the paired admin must accept, then runs in one shared DSH session with a persona attached, and the answer is posted back to the requester.