Plugins

Agent preset with adaptive tool presentation and environment-aware shell routing. Ports modules from yjh051108/dsh-routing-suite and xiaobright/dsh-anchored-standard (the former is listed here), so do not enable it alongside those presets. Requires DSH 0.2.2 or later; high uses PTC with on-demand tool unlocks and max uses PTC with the full available tool catalog.

DeepSeek Harness plugin: permanently delete archived sessions and their subagent logs. | DeepSeek Harness 插件：永久删除已归档会话及其子智能体日志。

让 DSH agent 识别微信/QQ 表情包与聊天截图并判断对方情绪（GLM-4V-Flash），暴露 wechat_emoji_analyze 工具。

Lets an AI play Slay the Spire 2: screenshot plus mouse/keyboard tools, a local card lookup, and a readable play log. Requires Windows and Python 3.10 or newer with Pillow.

Makes the agent answer as soon as it has one: injects a deliver-first rule into the system prompt and escalates reminders when tool calls pile up without an answer.

Per-conversation behavioral rule fence for DeepSeek Harness: rules live in one JSON file, are edited from a Settings page or the conversation panel, and every rule carries its own on/off switch so a single rule can be muted without deleting it (muted rules are skipped at injection and the remaining numbering stays contiguous); any number of conversations can also be excluded as a whole so they receive no fence at all, and picking conversations never touches the rules themselves; the enabled rules are injected as one runtime-context section at a fixed order so the system prompt prefix stays stable.

Read-only DSH profile doctor: the seven config-tree checks (config-clobber, dead-patch, tool-collision, plugin-not-mounted, plugin-stale, entry diff, explain) plus eight ecosystem checks learned from real failures — pnpm store version conflicts that break `dsh plugin add`, patch insert names node_modules cannot resolve, broken junctions, duplicate-capability plugins, orphan backup dirs, GitHub-source deps, npm publish-scope hints, and the minimumReleaseAgeExclude gap. Four agent tools; every finding carries its fix.

OpenFOAM case doctor for DeepSeek-Harness. Six agent tools: audit a case for 25 classes of silent failure (steadyState paired with timeStep writes, limiters set to 1 that let k/epsilon go negative, unbounded advection of transport scalars, nNonOrthogonalCorrectors 0 on a skewed mesh, loose solver tolerances, blockMesh vertex/block mismatch, stray time directories, purgeWrite 0); read any dictionary as JSON; survey a sweep of cases; run checkMesh/blockMesh/snappyHexMesh/foamRun inside WSL with log parsing; parse logs into the metrics that matter (aspect ratio, non-orthogonality, skewness, residual floor, fatal errors). Deterministic text analysis — no LLM — validated against a real 82k-cell street-canyon snappy case.

Audit how each turn's context budget is spent. Breaks down what a turn pays for AGENTS.md, the skill catalog, tool schemas and runtime context; flags repeated injection of unchanged content as pure waste; ranks skill-catalog bloat (with 60+ skills installed, how many tokens of descriptions does the model read every turn) and tool-schema inflation per plugin. Deterministic — no LLM, so a wrong answer is a rule bug with a name. Four tools including a cross-session sweep.

Audit what context compaction actually lost. Reads the raw session event log and checks session-constraint survival (the standing instructions the user gave — do-not-X, must-Y, only-in-Z — and whether the summary still carries them; arXiv 2608.11242 measured ~17% survival across compactors), summary hallucination (paths, versions, ports and identifiers the summary invents that were never in the history it replaced), ghost references ("see above" pointing at removed text), token accounting (a summary nearly as large as what it claims to free), and unaccounted prunes. Four agent tools including a cross-session sweep that ranks conversations by how much compaction hurt them. Deterministic — no LLM, so a wrong answer is a rule bug with a name.

Trimmed fork of ItQianChen/dsh-github-flow: a floating panel plus a right-column review pane for the pull requests raised in a session, showing CI state, review comments and merge status. It also registers the github_* agent tools (PR merge and review, secrets, raw API), so do not install both.

Beta: a project supervisor for DeepSeek Harness — standing rules plus a Web panel (three switches, dispatch modes) that splits a goal into parallel teammate dialogs, checks engineering baselines, interviews new-project requirements and protects beginners. The standing rules come from the repo kit installer, an optional separate step.

ZenTao work panel in the DSH left sidebar: lists tasks, bugs and stories assigned to you (web-login protocol, so instances where the RESTful v2 API is unavailable are supported — verified on ZenTao 18.13 open-source) with search, smart sort, overdue / due-today filters and a flow-board view (cards and details also show the owning project, execution, product and module, effort estimated / consumed / left, and the parent requirement or source bug); opens a new chat pre-filled with the card's description, recent comments and screenshots (or a blank one), or dispatches it to a new background session with workspace, model, reasoning-effort and optional-instruction selection (single or multi-select batch), turns screenshots inside ticket descriptions into real image attachments, reads back the linked session's latest reply once a card is done and lets you answer the agent from the panel while it waits on you, and tracks each card with live running / needs-decision / done status plus manual overrides and a manually-marked finished state, with a deep link to ZenTao's finish / resolve page, and caches list and detail data locally so reopening the panel or a card paints instantly with a silent refresh. Multi-account; read-only, no writes back to ZenTao.

Lets the agent see the compiled page: renders any page to an image, resolves a PDF point or a text anchor to the exact source line through SyncTeX (and says when a rule is drawn by a package rather than by the body, which is where naive locating is wrong), diffs a page against the previous build so an edit is visible, audits every page for holes the edit introduced, and checks that numbered labels still read in order.

Drives the DSH right-sidebar built-in browser from the agent side with 38 tools (open, navigate, read page text and interactive elements, accessibility tree, click, fill, select, check, key press, scroll, resize the browser frame by dragging its corner, with the page inside reflowing responsively so a narrowed frame shows the mobile layout, screenshot, full-page screenshot, PDF, markdown export, scrape to JSON, download, cookies, per-step operation records with replay and action whitelisting), serves the built-in web_search from a self-hosted SearXNG over an SSH tunnel with Tavily and a real-browser fallback, and registers a fetch provider that retries blocked GitHub URLs through measured mirrors and sniffs charset from the response header so GBK and GB2312 pages decode correctly.

Connects a ComfyUI server to the agent through five draw_* tools (status, workflows, models, generate, reverse) and a sidebar panel. It ships no workflows and assumes nothing about your models: every API-format JSON you drop into the workflow directory is inspected to find where prompt, negative, width, height, steps, cfg, seed and LoRA live, and a sidecar file can override what was detected. LoRA injection splices into any graph. All paths are configuration, editable from the panel and saved to a settings file, so it works against a remote or already-running ComfyUI. Headless auto-start and idle shutdown are opt-in and off by default.

Lets a DSH agent ask the user a structured question without blocking the turn: the ask_interactive_question tool returns a pending batch id at once, the answer arrives later as an ordinary user message, and pending batches sit in a browser inbox panel with optional system notifications.

Gives the agent 14 tools to create and edit DingTalk Yida apps (apps, forms, pages, schema, data) through the OpenYida CLI, plus a right-sidebar workbench that opens them in the built-in browser.

Sales workflow for individual insurance agents: P1-P5 product class matched against the client risk rating, a policy ledger that counts grace periods from the receipt date, and five-section dual-recording checks. 10 tools and 5 skills.

Run Blender headless from DeepSeek Harness: execute bpy scripts, render scenes and export glTF assets, with modeling cookbook, 5.x pitfall list and asset-pipeline playbooks bundled as skills so the agent self-checks geometry before handing assets back.

Drives Proteus 8/9 interactive simulation from the agent through eleven proteus_* tools: connect, simulation start/stop/status, probe readings, a project save that checks the file hash and mtime actually changed, and layout suggestions computed locally; on machines that register the Labcenter.InteractiveSimulation COM server it also places devices from a whitelist and queries and connects pins, while without COM it falls back to a keyboard-driven UI transport covering the simulation lifecycle and saving. Requires Windows with a local Proteus 8/9 installation.

Drives a local MaaEnd (MXU) client over its loopback HTTP API: 10 maend_* agent tools, a sidebar dashboard panel, and startup-mute / success-gated close-game steps in the task chain. Requires a local MaaEnd install with its MXU service running.

OneDev integration for dsh: an MCP server exposing the OneDev REST API as 61 tools — 57 administration tools (users, groups, roles, projects, authorizations, build agents and tokens, builds with streamed build logs, global settings, access tokens), 3 standalone documentation-query tools for docs.onedev.io, and environment discovery with per-call multi-environment routing — plus a dsh Web settings page that manages per-environment credentials locally and applies them on the next tool call without a restart.