Plugins

Three independent language channels for model output — tool-call descriptions (every tool-call card title, including run_code in PTC-style presets), thinking, and replies — each set to follow the web GUI language, force a specific language, or turn off (default: only descriptions, following the GUI). One global runtime-context prompt directive on the host; the client half reports the GUI language; a Settings plugin card switches the modes.

Forces periodic Engram memory recall and save reminders for DeepSeek Harness agents: injects a dynamic system-prompt context that reminds the model to load prior session memory at the start of a session, and to save new decisions/bugfixes/learnings every

Bundles the stack-diagram architecture-diagram skill as a runtime skill, and injects a system-prompt section so the model draws diagrams without being asked. Output is self-contained HTML plus light and dark PNGs from bundled Python scripts; brand logos are fetched at run time.

Adds one system-prompt section that limits delegation to subagents and teammates to two cases: adversarial review of freshly produced output, and one-shot context reading that returns a summary.

Read-only diagnostics for a DSH install — boot-crash logs and the cause named in them, config drift against a recorded fingerprint, backup freshness, workspace growth, plugin updates, host-version compatibility, duplicate client ids, and model availability — plus an action layer that always shows a plan first and needs a single-use fingerprint and explicit confirmation before anything is written. A checkup also runs 45 seconds after every host start; when the 3-hour probe cache is stale it sends a one-line test prompt to the default model and a few models of each configured provider (model.probeOnReport can switch this off). Registers the agent tools dsh_steward_report and dsh_steward_act (clean caches via dsh-disk-cleaner, backup via dsh-config-manager, disable or enable a bundle, set the default model; execute takes the plan's hash plus confirm: true) and a system-prompt section telling the agent to run the report first when something crashed.

Local-first memory nebula for DeepSeek Harness with graph views, evidence chains, hygiene checks, and offline snapshots. Reads the memory stores of every workspace and of other memory plugins (read-only, for example meow-memory's SQLite) and writes only under $DSH_HOME/memory-nebula. Registers 9 agent tools and a system-prompt section (usage rules every turn, plus not-yet-read neighbouring memories after a few reads); its /export and /share endpoints return the full memory text without authentication on the local server, and an optional standalone engine listens on 127.0.0.1:7890.

Adds a system-prompt section that asks the model to drop stock AI writing habits: subheadings, bold and emoji overload, quoted aphorisms and grand-finale endings.

Add one global prompt or persona that is injected into every new DeepSeek Harness conversation.

Standing GitHub-first open-source check: a system-prompt section makes the agent extract 1-4 keywords on every new request and make one cached, rate-limit-aware github_search call, so the answer can list up to five reusable repositories with stars, language, license, last push and topics.

Blocks tool calls whose description argument is not written in both Chinese and English: adds a system-prompt section stating the 中文:“…” 英文:“…” format and a tool guard that rejects English-only calls before they run. By default it checks every tool that declares a description parameter; set DSH_BILINGUAL_DESCRIPTION_SCOPE=shell to limit it to shell tools.

DeepSeek Harness plugin: a Task Instructions button beside the input box pins reusable task requirements to a session, and the instruction survives context compression.

Adds a switch to the left sidebar footer that toggles the assistant between a rigorous professional register and a relaxed, humorous one by registering a late bilingual system-prompt section; the mode is profile-wide, persists in DSH_HOME, and applies from the next request.

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.

Injects your own text into the DeepSeek Harness system prompt as real system sections from a sidebar editor: each section lands after the persona, after the tool docs, or at the very end of the prompt, can be switched on or off, and can resolve {{variables}}; a preview runs the host's own assemble and render pass so you see the exact prompt the next request will send, with empty, duplicate, unknown-variable and oversize sections flagged.

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.

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.

Quote books in the conversation header: one markdown file per chat, with search, a random pick, line and favourite counts, a keep button under every reply, and a trash with restore. The agent gets four tools (append, list, remove, merge) and a system-prompt guide, so by default it may save up to a line or two per chat on its own; capture rules can be set per chat or globally. Local-only. Needs DSH 0.2.1+ (below 0.3).

Adds a system-prompt rule that makes DSH agents look for existing work before they build.

Replaces the full skill catalog with keyword-based discovery, per-skill enable/disable switches, and system-prompt section controls. Disabled skills are refused by the skill tool, and their slash-command invocations are blocked at pre-step.

Registers a web-design skill and a compact system-prompt rule set for a three-layer shadcn/ui, Canvas UI and ThreeUI workflow, with Radix UI Colors and strict interface rules.

Multi-select system-prompt picker behind one bolt icon in the composer: check saved rows to inject in order, each scoped to main agent, sub-agents or both; every row (the built-in 「火力全开」, "Full Throttle", included) can be edited and deleted, and Clear all only unchecks every row without deleting anything.

Injects a configurable whale-girl persona into every DeepSeek Harness system prompt.

User-owned system-prompt insertion for DeepSeek Harness: place your own text at the head, middle, or tail of the assembled prompt, and edit it from a left-column Web panel with a live preview.

Xiaomi MiMo TTS voice plugin for DeepSeek Harness: speak a line through the local speakers, with a system-prompt reminder so the model speaks every turn, plus API key / voice design / preview controls in settings.