Plugins

External one-shot subagent provider using the local CodeBuddy CLI over ACP, with background result delivery and steering of running children.

TAPD + ZenTao task hub for DSH: list assigned work in the sidebar and dispatch an agent on a branch you name.

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.

Injects the non-obvious operating rules of Agent Teams into the Lead session through one ordered system-prompt section: plan the roster before spawning, roster slots are never released, write scopes are advisory, and wait_agent short-circuits when no peer is running.

Editable PowerPoint authoring workflow (a DSH-skill adaptation of icip-cas/PPTAgent) with concise Chinese business styling, HTML slide rendering and PPTX export review. Linux/WSL or macOS (Apple Silicon only); install LibreOffice, Chinese fonts, Node.js 22+ and uv first, then run the one-time setup, which creates a uv-managed Python 3.12 environment and installs Playwright Chromium.

Agent application development evaluation skill (skill bundle) for DeepSeek Harness: offline/online suites judged from audit side effects, baseline diff with zero tolerance for safety regressions, and mutation tests proving the evaluators themselves catch regressions. Framework-agnostic - needs a callable chat endpoint and queryable tool-call records. DSH host compatibility is deliberately undeclared.

Talk to DeepSeek Harness through Siri and iPhone Shortcuts: a bearer-key POST /siri endpoint on your computer answers each spoken request for Siri to read aloud, with a settings page (key, port, workspace, model, Agent Preset, rate limit, allowed addresses), optional DS Bot routing, and a ready-made Shortcut.

MiniCut tools for making multi-shot AI short films through the MiniCut CLI: status, next step, and run, with a price shown and the user's yes required before any paid job.

Windows desktop control for DeepSeek Harness: accessibility-tree snapshots, click by control name, delivery verdicts, and repeatable task files.

Cooking recipes in DSH: a full panel in the Web GUI plus four recipe_* tools for the agent. 373 home-cooking recipes — mostly Chinese, with Western, Japanese and Korean dishes mixed in — bundled with 347 dish photos and three kitchen-tip illustrations; the dataset is derived from the open-source HowToCook project (Unlicense) and was cleaned, unit-repaired and re-typeset for this plugin. Browse by dish, category or the ingredients you already have, get a daily pick, keep favourites and cooked marks, and read kitchen tips. Everything ships inside the plugin: offline, no hotlinking, no telemetry.

Workout logging plugin: a fitness_log agent tool (log, history, stats, weekly plans) storing data in local SQLite; the repo also ships a separate optional left-rail panel bundle under ui/.

macOS Computer Use for DeepSeek Harness: the agent reads accessibility trees, captures screenshots and drives real desktop apps, mounted on the 0.2.1-rc.5 line with a separately built native helper. macOS only.

Local media toolbox for DeepSeek Harness: converts files between 27 video, audio and image formats, trims clips, extracts audio or video tracks without re-encoding, exports embedded subtitles to .srt, compresses images with a before/after preview, reads and rewrites metadata, and encodes or decodes Base64 — all through the ffmpeg already installed on the machine, so files never leave it. The same engine is registered as a media_toolbox tool agents can call.

Layered memory for AI agents: five verbs (wake/work/pit/tomb/close), core layer read every time, archive on demand. Plain markdown, four pages created on first run; survives restarts, model swaps and plugin removal.

Runs Hindsight long-term memory on your own machine: after a one-time uvx --from hindsight-embed@latest hindsight-embed profile create server setup (~450 MB of Python dependencies) and with your own LLM key, the plugin manages the local memory server itself (health probe, start, stop, logs), registers ten hindsight_local_* tools for status, page search, page read, recall, remember and reflect, injects a knowledge-page index once per session, writes each finished turn back into the bank, and extracts facts with your own LLM key. Do not enable it alongside the official @vectorize-io/hindsight-coding-agents plugin: both read the same bank and would inject duplicate context. At session end it writes a handoff snapshot that the next session injects as previous progress. The data directory is configurable (dataDir) and scripts/relocate.mjs moves an existing install to another drive, creating directory junctions where the server hard-codes its paths.

PTC agent preset whose tools.guard refuses tool calls until the session holds an active goal and an in-progress todo.

Gives an agent tools to open foreground sessions, prompt them in queue or steer mode, read the transcript back, cancel a turn, and get the authenticated URL of the local web app.

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.

Give your agent an external emotion state machine: several axes (0-100) that drift over time and move when you speak to it. Each turn the plugin injects which band you are in plus which tags you may use. The numbers belong to the plugin: the model reads them from the injected prompt and can change them only through the plugin's own emotion tools, never by asserting a mood.

After user setup, guides native subagents toward model preferences by task type, using native model-selection permissions with no extra routing-model calls.

TeleAgent (China Telecom TeleAI "Stellar" agent) model provider for DeepSeek Harness with the working v1 gateway signing: two-round HMAC-SHA256 keyed by the login JWT signature segment, which fixes the 40104 rejections the older local-v1 signing produced. Signs in through a dedicated browser window over the DevTools protocol — the plugin intercepts the login callback the same way the official desktop app does, so nothing has to be copied by hand — and also accepts a pasted token. Ships points balance, daily check-in, an in-composer account chip, and a configurable context window (100K by default, 16K–2M, since the gateway declares no catalogue and the official client ships one shared 100K preset for all three tiers). Cannot be installed alongside anye-99/dsh-codearts-auth: both register the same teleagent provider, and this plugin reuses its credentials and derives its SSE/tool-call parsing from it. It also registers the same teleagent provider as anbulang/dsh-connect-teleagent, so install only one of the two.

Makes the agent narrate progress during long tool chains instead of staying silent until the final answer: a standing system-prompt rule that travels with every request, plus a notice injected after every N tool calls. A panel on the plugin page tunes the cadence, the reminder budget, and both texts; changes apply live.

Create and edit your own Agent presets with a form in Settings, covering id, name, description, order, and the plugin composition.

MCP server panel for the DeepSeek Harness Web GUI: the sidebar lists every @deepseek-ai/dsh-mcp-client row — including rows inserted by other plugins — and derives its connection state from the loader fiber, the mcp__<server>__* tools still registered, a TCP probe of HTTP endpoints and the last connection test; it shows the row's configuration, enables or disables it by editing only that row of the patch file, reconnects once after a failed attempt, and reports unavailable servers to the agent through a system-prompt note plus a call gate that refuses their tools instead of letting each call fail at the transport.