Plugins

Second-model gate on the assistant turn, installed with one command: the bundle installs the settings panel and mounts the engine out of the same package, so both halves come up together. A separate judge call scores the draft against the numbered criteria (0-10 each); any criterion under 6 fails the turn and sends it back for a rewrite, up to 3 rounds by default. Ships in dry-run mode, which only records verdicts to an audit log until you switch it off. The web panel edits the criteria, the thresholds and the judge prompt.

Reader-first long-form fiction pipeline: setting and character cards first, 21 gate scripts, a 1000-trope library and 700 theme seeds, at most two tropes per chapter, a self-test for every script; the scripts run on the host's Python 3.

Dynamics 365 CE / Dataverse toolkit for DSH: 15 tools for querying metadata and solution layers across environments, snapshots and diffs, field impact analysis, migration risk assessment, GitLab merge-request checks, contract drift, environment health, and review-gated metadata writes.

A consent-gated personal profile store: people are indexed by name, entries by person and key, and no profile record is read before the current session is authorised. Sensitive entries come back masked unless the user authorises that tier separately; credential-like values are refused at write time. Ages and next birthdays are computed at read time, so asOf restores the answer for a past date, and facts that rot (height, weight, address) carry freshness warnings. Five profile_* tools plus a settings page to browse, edit, delete and revoke grants.

WEB ONLY: designed specifically for the Web profile, NOT Electron Desktop. Windows support means Web on Windows, not the Desktop application; installing into Desktop can break startup or restart. Refresh immediately after installation or open /login; HTTP 401 on an old page means sign-in is required, not installation failure. Only an uninitialized data directory displays the temporary password; existing passwords survive reinstalling. Initialize in a trusted network and change the publicly displayed initial password immediately; passwords are never printed in terminal logs. Web lock screen, password/OTP/Passkey, persistent sessions and wallpapers; Windows Web power services can be enabled from the page. Linux/macOS need the bundled controller; npm updates require a dedicated managed install. Stopping interrupts active tasks. Auth kernel adapted from xbzbing/dsh-auth-gateway (MIT); do not co-install.

Read-only knowledge gateway over a local Markdown vault, in four tools: `wiki_recall` returns the matching section in full with page-level citations plus vault health checks and a page skeleton for writing a good answer back; `wiki_context` returns one evidence pack with per-page excerpts, a support verdict and an explicit list of gaps; `wiki_verify` re-checks a drafted answer against that pack and reports claims the evidence cannot back, including unsupported numbers; `wiki_observe` reports how often answers needed correcting. The settings page and sidebar panel share the same query path as the model, so a search you run by hand cannot disagree with what the model was given. The three knowledge-gateway tools (`wiki_context`, `wiki_verify`, `wiki_observe`) need a local Python 3 bridge — `bridge.python` plus `bridge.toolsRoot` containing `wiki_bridge.py`; without it they return `E_PYTHON_UNAVAILABLE`.

Self-narrative memory in five budgeted segments (800 chars, not a full context): a first-person note the model writes to itself, a profile of you aggregated from approved facts, environment facts kept separate from who you are, heat-ranked conclusions, and habits. Every injected fact is traceable to a fact id and can be retired; the profile can be edited by hand, and self-notes stay plain lines you can clear. Facts fade by use and time without ever changing their credibility. Preference-like lines you say are auto-detected as candidates (never auto-approved), with conflicts kept side by side. Recall over past conversations with citations, an incremental index that only decodes newly appended frames, a pointer-required warm layer, a doctor that says which part is broken, a heartbeat proving injection is alive, and export/import so the whole thing moves to another machine.

Loads a workspace's VSCode/Copilot AI configuration into every DSH session: `.github/copilot-instructions.md` is injected as standing instructions, `.github/instructions/**/*.instructions.md` are gated by their frontmatter `applyTo` and join once the session has touched a matching file, and `.github/skills/*/SKILL.md` are registered as DSH skills. Configuration directories outside the workspace, by default `~/.copilot`, are read as well, and a settings page edits that path list.

DSH plugin: plain-language narration, an uncertainty gate, and mid-run interruption policy for DeepSeek Harness agents.

Delegate subtasks to Herdr-managed coding agents from DeepSeek Harness: pick the model, keep the pane, harvest the exact result, review in DSH.

Verification gate for DeepSeek Harness: run typecheck/lint/tests after edits, and keep the agent working until they pass.

Batch approvals with a risk gate and an auditable decision ledger for DeepSeek Harness.

Novel writing engine for DeepSeek Harness: state machine, gates, rulepacks and ledgers moved from prompts into code.

Road building materials as a caliber manual: 60 cards over 12 chapters on aggregates, asphalt and the PG system, mix volumetrics, cement, concrete, stabilized mixtures, steel, polymers and 35 test procedures.

One MCP tool surface over two Windows desktop-automation backends (dsh-computer-use-win and windows-mcp). Both must be installed first: dsh-computer-use-win as a DSH plugin, windows-mcp via uv tool install windows-mcp --python 3.14, then run the bundled scripts/patch-backend.mjs once (it rewrites the local windows-mcp source; without it screenshot/read_webpage/launch_app fail) and disable the standalone wincu mount. It merges their 44 tools into 29 by dropping 10 duplicates, 4 dangerous ones (PowerShell, Registry, FileSystem, Process) and 1 tool-management entry, and blocks dangerous calls before forwarding through a reversibility-graded guard.

Mounts the REA (Reverse Engineer Anything) MCP server through two gateway tools instead of registering its 200+ tool schemas on every request: rea_list searches the catalog or returns one tool's input schema, and rea_call invokes that tool, each call spawning a short-lived rea mcp process, so the tool definitions sent per step drop from about 780 KB (207 tools as measured in REA 6.5.0) to about 1-2 KB. When no rea entry point is found it installs rea-agents into a plugin-private directory with the pnpm bundled in DSH (dependency build scripts skipped) and links the reverse-engineer-anything and rea-gateway skills into the skills directory without overwriting existing ones.

Runs the locally installed ZCode CLI as a `zcode` model route in DSH: all traffic is signed by the official binary, the plugin never sends its own request, forges client requests or sends credentials off the machine (the plan token is decrypted in memory only to hand back to the official CLI), no API key is needed, and both a paid one-shot and a free app-server channel are supported. Since v0.3.0 it ships an HTTP MCP bridge so tool calls run through the DSH approval surface. Backed by a contract document and a node --test gate.

Registers the workbuddy model provider by mounting dsh-llm-workbuddy and supervises the local wb2api gateway, then bundles two protocol bridges onto that same gateway: Responses for OpenAI Codex CLI, and Anthropic Messages for Claude Code and Claude Desktop, which see the gateway models under generated claude-wb-… ids. Skips work that is already running or already registered, and reports each part through a status tool. Requires a local wb2api gateway and a WorkBuddy account.

Qoder supplier plugin for dsh-router, covering both the CN and international regions. Uses a personal access token for authentication, signs requests to the Qoder cosy gateway and converts upstream SSE to OpenAI SSE; the model list reports the upstream display name alongside the key, while account selection and cooldown stay in dsh-router core.

DeepSeek Harness 对话内容搜索插件：在 Web UI 内搜索当前与全部历史会话的消息文本，点击结果自动切换/滚动定位到命中消息并高亮，面板内展示命中消息的前后上下文。Conversation full-text search for DeepSeek Harness: search the current and all historical sessions, click a hit to auto-navigate, scroll to and highlight the matchi

Drive DSH's own built-in browser (the right-hand Sidebar's Browser tab) from the agent: list tabs, open, navigate, read the page, run JavaScript, click, fill forms, log in, and look at pictures or the pane itself with vision. No second Chromium process.

Read-only Automations tab in the conversation view. It aggregates what other plugins are scheduled to run: last run time, next run time and a rough token-cost estimate, plus today's total spend and remaining balance. It owns no tasks and starts nothing.

Bilibili autopilot run by a local Ollama model: it picks videos within per-topic quota, reads subtitles, hot comments and keyframes, decides whether a reply is warranted, then writes and posts one comment through a five-level safety gate. Triggered by dsh-schedule; write tools are not registered while commenting is disabled. v1.1 hardens the write path: revoking write access is a runtime state checked before every send, publishing is atomic, risk-control errors persist as a pause, and the final post re-checks persona style. Needs Python 3.10+ with the repo's requirements.txt installed.

Standalone QQ-bot extension pack for DeepSeek Harness — fully independent, no other plugin required. Two-layer SQLite memory with hippocampal recall, a persona that keeps learning from daily chats, group tiers, local-model quick replies with a single-brain arbiter, TTS outbox, sticker library, an approval-gated video studio, and a four-form desktop pet (three custom characters plus the stock fish) playable over a public invite link with access-code login, single seat and brute-force protection. Chat bridging is deny-by-default: c2c/group access defaults to a care mode that only responds to the special-cared people and groups of the owner (shared with the persona system, zero extra config); allowlist, open and disabled modes remain available. First-run defaults (persistent inbound dedupe, configurable outbound-hook budget, optional default permission preset, extension seeding) are written only where nothing was configured and never overwrite user changes. Interview and quiz practice run inside chat with local scoring and configurable transcript retention. Requires QQBOT_APPID and QQBOT_SECRET, and Node.js 22.5 or newer.