Category · workflow
Workflow & Automation
Plugins for orchestration, scheduling and automation.
200 plugins
Runs a local OpenAI-compatible gateway so DSH can use the model quota of a logged-in Tencent CodeBuddy (WorkBuddy) account: one-shot installer with SHA256 verification, logon scheduled task with duplicate-launch guard, manage.ps1 for status/start/stop/restart/logs/update/uninstall, and an agent skill that drives setup and troubleshooting.
可在对话内生成、编辑、对比图像;内置 500 + 提示词、图库、多模型工作流,支持 ComfyUI。AI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+ prompts, gallery, multi-model workflows and ComfyUI.
Optimized fork of dsh-image-gen with batch generation (count), gallery pagination, lazy loading, fetch retry/timeout, and 7 providers: Gemini/OpenAI/Seedream/DashScope/Agnes/GLM-Image/Stability AI.
dsh-agent-teams turns the current DeepSeek Harness session into a captain that can assemble durable sub-agents, split a goal into dependency-aware tasks, and coordinate work through direct messages.
DSH Automation is a community-maintained DeepSeek Harness (DSH) plugin, not an official DeepSeek AI product.
Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.
AgentCompare compares 2–4 answers, files or live pages in the DSH Desktop/Web main conversation, with Chinese/English UI, shared conversation context, blind or open picks and reviewed adoption. Requires a root-level Vite project in a Git repository with at least one commit.
Lets the agent start a conversation on its own, using a local dice roll on a set interval to decide whether to speak into a chosen session, with quiet hours and a dry-run mode.
Schedules a daily, weekly or monthly GitHub Trending digest, has a local trendradar core write Chinese summaries and period recaps, commits them to your own repo and opens the pull request, and shows an overview, digest, run history, subscription and settings workbench.
A verifiable roster layer for DeepSeek Harness Agent Teams — review personas, models and tool boundaries before you build, verify after, write drift back. 建团队前可 review、建完能核、跑偏能回写。 Operated by AI: issues, PRs and releases are handled by an agent. 日常运维(issue / PR / 发版)由 AI 自主完成。
The DSH plugin-development knowledge base as an on-demand agent skill: official constraints, task workflows, API reference and community gotchas, installed with the bundle so the agent can look things up while building a plugin.
Automated Cron Scheduling, Background Automation & Agent Execution Engine for DeepSeek Harness
AI image and video generation for the DSH Web GUI: text-to-image and image-to-image over per-channel model catalogs with per-family request shaping (gpt-image, Grok Imagine, Nano Banana, Seedream, GLM-Image, Qwen-Image, MiniMax image-01, DALL-E 3), a sidebar generation studio, an infinite canvas with node workflows, files preview and canvas skills, and a prompt template library; the video side adds text-to-video, image-to-video, first/last-keyframe and multi-reference modes on an async submit/poll/download pipeline, host-side video tools, video nodes on the canvas, and clip stitching of two or more video nodes into one MP4 with the local ffmpeg.
Novel-writing guardrails: 24 novel_* tools enforce fact-ledger consistency, outline and chapter gates, a deterministic machine audit with a zero-token AI-flavor scan, and proposal-only revisions; a right-panel workbench covers reading, TTS playback, whole-book checks and batch drafting with checkpoint resume.
Novel-writing workbench for DSH with an authoring preset, outline and character management, manuscript annotations, review workflows, and a managed local Python backend.
Deep PTC mode is an open-source agent preset for DeepSeek Harness that keeps the built-in PTC tool surface and replaces the persona with a working contract: a DeepSeek identity and unlimited-token-budget instruction so the model does not skip reads, commands or checks to save tokens; planning by estimated size (internal up to 5 minutes, shown without approval up to 20, approval required beyond); and asking about unclear intent instead of guessing. Waiting is limited in code by wrapping the official shell, job and question tools: foreground commands move to background jobs after 30 s (configurable), a steered user message ends the current wait so the model reads it, foreground pauses over 5 s and long timers in run_code are refused, and questions run in timed mode. The mode derives its preset from the official PTC declaration shipped by the installed Harness and inherits upstream composition changes, so an official PTC update — including removed or renamed modules — does not break existing sessions. A settings card selects the preset executor — Automatic, WSL Bash, Windows PowerShell, native Zsh or native Bash.
Durable task-decomposition plans for DeepSeek Harness with a self-learning loop: every department subtask runs in three ordered phases (plan, execute, verify), the verify phase must submit a retrospective of problems, detours and resolutions, and that retrospective is written to a permanent lessons file, ranked against the new subtask and injected into later dispatches so the same mistake is not repeated. Adds a read-only dsh_workplan_lessons tool (11 model tools in total), a progress panel drawn as a ring, a stacked bar and per-stage steps, and a public ISO/IEC 15408:2026 security self-assessment with zero runtime dependencies.
Drive a local or remote ComfyUI server from DeepSeek Harness: comfyui_run / comfyui_object_info / comfyui_workflow tools generate and edit images and videos, with a workflow library (graph extraction: per component / main flow / all), a load area with resolution auto-match, a live queue, SDXL and Wan 2.1 templates, a companion skill, and a same-origin media proxy.
DSH sidebar image-generation workbench with illustration and photography pipelines, a built-in local account pool, and any OpenAI-compatible endpoint.
Disclaimer: This is an unofficial third-party tool. It is not affiliated with, endorsed by, or sponsored by DeepSeek or the DeepSeek Harness project. "DeepSeek" and "DeepSeek Harness" are trademarks of their respective owners. This project only orchestrates the workflow tool available in your DSH environment; it does not redistribute any DeepSeek software.
Your AI learning companion: helping you plan your studies, understand concepts, and build projects to master a subject.
Task board for DSH: create tasks with project and model assignment, run them manually or on cron schedules; new sessions in a project automatically pick up its todo tasks and move them to in-review when done.
A local-first issue board plugin for DeepSeek Harness (dsh). It embeds a complete task board — Kanban / list / Gantt / workflow / dashboard views plus per-task AI chat — into the DSH Web GUI. Data lives in a local SQLite database (/.dsh/storages/dsh-taskboard/taskboard.sqlite); no external service, no cloud dependency.
All-in-one combo patch for STARDUSTLC's 18 DSH plugins: one command injects shared default configs across office, media, DevOps and notification presets; each component installs directly via a one-line add command (flat design, no git subdependencies).
Windows only: the agent edits documents inside the Word, Excel and PowerPoint (Microsoft Office or WPS Office) windows you have open, through the applications' automation interface, so changes appear live and you can edit alongside; it reads structure, applies batches of edits, renders pages to images to check layout, and saves or exports PDF.
Verifiable research-report engine for DeepSeek Harness with a content-addressed evidence ledger, versioned sealed reports where every claim carries a verification verdict and the manifest hash seals the directory, and retrieval orchestration that reuses the ctx.web and ctx.jobs seams.
Sync DSH user-level assets (skills, plugin manifest, config, memory) across machines with one-click restore, automatic plugin reinstall and secret scanning.
Declarative DAG runtime for DSH tool plans with bounded parallel execution, read-only retries, per-step checkpoints, cancellation, and conservative crash recovery.
Multi-agent orchestration agent preset for DeepSeek Harness: one chief orchestrator that never implements itself — it triages every request, has a PM expert plan the work, and delegates implementation to domain experts via a merged expert roster (list and summon tools), scheduling parallel work through a dependency-DAG taskboard and a file-based message bus, with delivery gated by an independent review. Ships 11 core experts; more expert teams (Agency agents EN/ZH, classic collections) are one-click downloads from the settings page over dual GitHub/CDN channels with sha256 verification. Published on npm as dsh-expert-orchestrator (requires DSH >= 0.1.7-alpha.2).
System-1 decision guard for DeepSeek Harness, 4 questions asked before tool calling (risk reversible, relevance, injection suspension) and allow/ask/reject action. Needs an API key for a system-one compatible provider; decision requests are sent there.
Personal assistant for projects, conversations, memory, reviews and news. Bundled WeChat pins the QR-confirmed account; first messages cannot claim ownership. An optional allowlist further restricts access. Missing or conflicting identity requires desktop recovery. API acceptance is not phone receipt.
Version compatibility (0.5.4): Targets DSH 0.2.2-rc.1. This patch corrects dependency flow and opens teammate sessions from task titles and member cards; it retains the per-office model selection fix before the host freezes each step; 0.5.1/0.5.2 only repaired preset loading and display metadata. Verified with official host components and isolated profiles, without real model calls; see the model regression scope below. Earlier rc.3/rc.5 UI and installation results are historical evidence for ea
Engineering-discipline guard: requirements grill before the first edit, red/green test-evidence gates, forked adversary review, and a delivery report with a per-dimension verification workflow.
Long-lived AI companions with isolated memory, WeChat channels, Skills, schedules, heartbeat concerns, and a dependency-aware task board.
Workflow and automation (`workflow`): task dispatch, optional Agent Teams, and tiered verification; usage and billing (`usage`): session token tracking and automatic context folding (no bill calculation); sessions and messages (`session`): persistent fold state, protected recent messages, and watermark-triggered handoff; models and account access (`model`): six dispatch pools and optional intent-based routing (no account integration); skills (`skill`): read-only MySQL/Redis checks, commit-message generation, and requirements/design docs; development and runtime (`dev`): Host/Client settings UI and tool-call safeguards. Together, these features are designed to balance output quality with token efficiency and model-use costs.
--- AIGC: ContentProducer: '001191110102MAD55U9H0F10002' ContentPropagator: '001191110102MAD55U9H0F10002' Label: '1' ProduceID: '69910f2e-fa01-4336-80c6-96a88da0868e' PropagateID: '69910f2e-fa01-4336-80c6-96a88da0868e' ReservedCode1: '2027e396-94f6-468b-bbee-37e2c84c163a' ReservedCode2: '2027e396-94f6-468b-bbee-37e2c84c163a' ---
A standalone dsh (DeepSeek Harness) plugin bundle porting the omp "advisor" subsystem: a per-session independent reviewer model that observes the primary transcript, reviews each stepped turn with an explicitly configured model (provider + model are required), and injects severity-ranked advice (nit / concern / blocker) back into the session — without polluting or recursively reviewing itself.
A standalone dsh (DeepSeek Harness) plugin bundle porting the omp "advisor" subsystem: a per-session independent reviewer model that observes the primary transcript, reviews each stepped turn with an explicitly configured model (provider + model are required), and injects severity-ranked advice (nit / concern / blocker) back into the session — without polluting or recursively reviewing itself.
一个更快、更节省、更准确的 DeepSeek Harness 插编码件。在 SWE-bench Pro 最难的 100 道题中,回答耗时减少21.8%,每题token减少34.6%,正确率甚至增加了6.5%。A faster, more accurate, and more cost-effective DeepSeek Harness plug-in component. Among the 100 most difficult questions in SWE-bench Pro, the response time -21.8%, tokens per question -34.6%, and the accuracy rate even +6.5%.
Cuigengji, your fiction-writing assistant and editor: organize settings, develop plots, draft chapters, and revise prose with AI. Share plot canvases, character cards, and worldbooks while you choose the direction, style, and what stays in the story.
Gated multi-agent pipeline for OpenSpec changes — six opx_* tools drive the phase state machine, two agent presets (developer and reviewer) carry implementation and review, and 23 bundled skills define the quality standards they are checked against; full mode runs analyze, implement, then tool, task and dimension-based quality review, while simple mode runs implement and one merged quality review.
Integrates coding agent CLIs, persistent terminals and remote workspaces into the native DeepSeek Harness interface.
Minimal prompt x Web PTC capabilities: one-line persona, run_code SDK, subagents, Ralph, web search/fetch, and Windows Git Bash; the general-purpose workflow tool stays hidden.
dsh-agent-team gives DeepSeek Harness agents that don't reset. Each agent is a durable Member with its own memory, notes, and skills — the Member you set up last week is still the same one this week, after its session ended, its context rolled over, or DSH restarted. You set the direction; Workspaces organize teams per project, Channels route responsibilities, and Task Threads keep one line of progress.
Minecraft development for DeepSeek Harness (dsh), covering Minecraft 1.7.10 through 26.3: 9 skills for Paper/Spigot plugins, Fabric, Forge and NeoForge mods, addon development against major mods, and Gradle/JDK setup per era; the mc_scaffold generator and mc_gradle runner; 18 offline API signature indexes generated from the pinned artefacts with provenance headers; and mc_arbitrate, a deterministic sharded pipeline (contract freeze, per-shard briefs, 21 high-confidence audit rules including 5 cross-shard checks, manifest merge, compile-error routing) that calls no model inside the engine. Apache-2.0 with NOTICE.
Preset engineering workflows for DeepSeek Harness: a dev_task tool that gates stage transitions, artifacts, verification, review and commit scope, plus a web workbench for installing project or user skills and rules.
Reflex arc for DS Bot: runs as a sibling DSH plugin with no change to ds-bot, collects facts in cheap layers, scores them with a local decision model, and wakes a Bot only when something crosses a threshold.
Human-led Kanban and AI-run workflows in one DSH plugin. Manage workspace tasks together with agents using draggable cards, search, priorities, labels, due dates, Markdown, images and comments. Create and edit reusable workflows through chat, configure stage models, and let AI execute each stage with DSH tools and permissions. Follow progress on a flowchart, inspect native stage conversations, approve results or send them back with feedback, and retry failed stages or terminate tasks. Preview files in each task's own artifact directory and use execution history and review feedback to improve workflows for future tasks.
dsh 桌面端的 iterate 质量指挥中心 + 经验银行插件(v3.2)。把 iterate 生态的同一套 review/fix loop 直接搬进 dsh 界面,新增质量门禁、经验银行、防御事件流与原生指挥操作。 The iterate ecosystem's quality command center + experience bank plugin for dsh (v3.2). Natively embedded inside the DeepSeek Harness (dsh) desktop client with quality gates, experience bank, defense events stream, and native command buttons.
Scheduled reminders and delayed send for DSH: /later delivers what you type as yourself at the time you pick, while the timer panel (or /schedule) posts a reminder row — even with the page closed. (scheduled send / reminders / delayed send)
Scheduled reminders and delayed send for DSH: /later delivers what you type as yourself at the time you pick, while the timer panel (or /schedule) posts a reminder row — even with the page closed. (scheduled send / reminders / delayed send)
A DeepSeek Harness plugin bundle: eleven specialist roles usable as one-shot consults or as team members, a team plane with a plan, a shared board and a dependency graph, a durable workmate library, a memory engine, and a verification plane that refuses a PASS unless a different agent records the verdict against gate evidence. Installs as one package with a dsh.bundle patch; also ships a native dshGo panel interface and a conformance gate pinned to a dsh-Go protocol v1 spec commit (d5ad25c).
Multi-agent orchestration layer for DeepSeek Harness — autopilot/ralph/team execution modes, 19 role cards, 40 bilingual skills, and a bundled MCP state server, ported from oh-my-claudecode.
A work mode for DSH in which the main conversation does exactly three things: understand what you asked for, turn it into task briefs, and report back what the Subagents concluded. Every piece of process data — file contents, command output, build logs, search results, dead ends — is digested inside a Subagent's context and never enters the main one. The main conversation therefore holds only high-value information.
Official repository. The only official repository of this package, maintained by PerryLink. Same-name repositories under other accounts are not affiliated. Apache-2.0.
Owner workbench for independently connected family WeChat assistants, per-member project and tool permissions, scheduled services and delivery status; API acceptance does not confirm receipt.
Manage Claude Code, Codex and Grok CLIs inside dsh and dispatch tasks to them as headless subagents, with dsh models, skills and tools bridged into each task, resumable CLI subsessions, and a hierarchical task board in the right sidebar (the board tab requires the separate DSH-better-sidebar plugin; without it the tab is not registered).
Schedule a message into a dsh chat for later: a Schedule button in the message box with a date and time picker, a sidebar panel of pending messages across chats, delivery as a normal user message even with the browser closed, and schedule_message, list_scheduled_messages and cancel_scheduled_message tools so the model can come back to a chat on its own.
Calendar and hierarchical task workbench: AI-assisted intake clarification, consultation, decomposition, execution with user acceptance, and review, plus reminders and per-task AI session workspaces.
dsh-claude runs the locally installed Claude Code CLI as a first-class conversation provider inside DeepSeek Harness (DSH). It uses Claude Code's official Agent SDK protocol instead of recreating the agent with a separate API client.
Bundles 19 short-video production skills (1 entry point, 1 orchestration, 17 atomic) into the agent skill catalog: Chinese TTS pronunciation fixes, text-to-image and text-to-video, image panning, composition, covers, media verification, data review and four-platform publishing. Ships skills and scripts only, so a runnable pipeline still needs ffmpeg, Python 3 + Pillow, Node.js and playwright installed locally, your own Bilibili biliup credential and WeChat Channels / Douyin / Xiaohongshu login states, and the placeholder values under skills/*/scripts/ filled in with your own. An installer's own skill of the same name keeps precedence.
Autonomic heartbeat for each root agent: silent pulses diff the session's todos, Agent Team board and goal against what the last pulse saw, and speak only on a signal — L1 report, L2 ask (ask_user_question), L4 escalate — never starting work. Each message carries a why-now line, an optional one-line physiology signature (time since your last message and how many times it has reached out today) and a compact task snapshot (800-char cap); a dedupe window, quiet hours, a daily budget, refractory/restart cooldowns and persisted vitals keep it quiet, while busy-safe followup injection never stacks. It shares one advisory speech floor with dsh-plugin-memory (~/.dsh/proactive-cooldown.json, 180 s) so the two never talk over each other, stays silent while a child subagent or teammate is still working, and surfaces a "subagents working · N" pill in the conversation header (polling pauses while the tab is hidden). v0.8 adds a diagnostics panel that explains recent quiet pulses and names the current speech-floor holder, plus panel controls for the arbitration window, presence suppression and the physiology line; its settings section carries a stroked heart mark (16×16, stroke 1.3, same spec as dsh-plugin-memory). v0.8.1 makes the plugin compatible with DSH 0.2.2-rc.2: the agent registry is read with agents.roots() when available and falls back to agents.list() on rc.2, and every agent/created listener is exception-guarded — on rc.2 an unguarded throw there rejects agent registration and no session can be created, so rc.2 users must upgrade to 0.8.1 or newer.
Trellis-style workflow for DeepSeek Harness: per-turn phase breadcrumbs via agent/pre-step, bundled skill provider, and DSH-native task/phase state with git-cleanliness guardrails.
Official repository. The only official repository of this package, maintained by PerryLink. Same-name repositories under other accounts are not affiliated. Apache-2.0.
Reusable Agent Team presets for DeepSeek Harness: a Settings page stores named Teams — a captain with its own prompt and tool allow-list, plus members carrying their own provider/model route, reasoning effort, prompt and tools — and a composer control applies one Team to the current Session, installing the captain prompt and registering the spawn_team_member, get_team_preset and update_team_preset tools.
Travel expense reconciliation: ingest orders, invoices and card lines, deduplicate, run the three-way match and a read-only policy check, then export — 5 `travel.*` tools.
- Lean & Responsive: Removes heavy orchestration layers (no present deliverables, goals, complex plan modes, sub-agents, or TODO trackers). Focuses purely on fast, direct coding cycles. - Essential Tooling: Retains core tools needed for day-to-day software development: - File reading, editing, and fast directory scanning (fs, fs-search) - Full-featured Bash execution (tool-bash) - Background asynchronous task management (tool-jobs) - External skill packs support (skill-filesystem, tool-skill) -
What if you could take the coding agent you already have — Codex, Claude Code, Gemini, OpenCode, Cursor, a local model, a cheaper model, whatever you happen to use — and make it work more like a serious coding partner?
Multi-CLI worker sidebar for DeepSeek Harness 0.2.0-rc.2 on macOS and Windows, with task dispatch, live conversation views, stop and follow-up controls, and custom role presets.
AI project board for DeepSeek Harness: turns sessions into tasks, tracking progress, blockers, acceptance criteria, and deliverables across full-page, sidebar, and floating views. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
HarmonyOS delivery orchestration for DSH: freezes a four-dimension acceptance pack whose measurable criteria carry machine-checkable assertions, runs an adversarial pre-review before dispatch, hands the work to DevEco Code in Goal mode, then audits the delivery with independently gathered evidence (screenshots, UI tree, logs, hashed evidence bundle), recomputing assertion verdicts against measured values and filing rework orders; includes a cited rule catalog, a user-confirmation state and a gate calibration ledger.
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.
OMC-style multi-agent orchestration for DeepSeek Harness: 29 omd-* skills and 12 /omd-* slash commands over the plan-execute-review-verify pipeline and team/autopilot/ralph modes.
Visually configure an agent's prompt, tools, visible skills, subagents and fallback models, and assemble several of them into a team. It never writes or edits any host preset file.
Lead-mode agent preset plus two runtime skills for the official Agent Teams runtime: a delegate-wait-verify working method, and a wrap-up digest that merges several members' output into one file. Ships no team runtime of its own.
基于 DeepSeek Harness 的多 Agent PTES 渗透测试编排插件,支持自动化侦察、漏洞分析、验证与报告,使用 Docker/Kali 隔离工具箱 | Multi-agent PTES penetration testing plugin for DeepSeek Harness with automated recon, vulnerability analysis, validation, reporting, and Docker/Kali toolbox
Official repository. The only official repository of this package, maintained by PerryLink. Same-name repositories under other accounts are not affiliated. Apache-2.0.
Official repository. The only official repository of this package, maintained by PerryLink. Same-name repositories under other accounts are not affiliated. Apache-2.0.
Step-by-step workflow map for DeepSeek Harness: folds a session into one step list, labels where each percentage came from rather than reporting a bare number, and queues a prompt for the next step with revoke before it is claimed.
One dsh host plugin: a single table of task definitions drives your recurring agent work — when a task is due, it is dispatched as an independent dsh session that an agent actually executes. The scheduling itself is pure program logic and never burns a token.
Official repository. The only official repository of this package, maintained by PerryLink. Same-name repositories under other accounts are not affiliated. Apache-2.0.
Installs four multi-agent math-research presets for DSH: v2 (probability-driven pipeline with multi-verifier debate), v3 (paper-style Markdown knowledge base with a planner agent and a reusable method library), v4 (persistent self-organizing residents that message and meet), and v5 (a research institute with an academician who decomposes and assigns work, voting researchers, temp workers, group chat and a compare-and-set task board); all four support checkpoint resume, human intervention, and an optional Lean formal-verification switch (off/encourage/require) whose passing proof turns the vote into a fidelity check of the Lean statements.
A port of oh-my-opencode-slim's specialist subagent delegation for DeepSeek Harness (DSH): an orchestrator + 5 specialist roles, each with its own persona, model, tool permissions (toolFilter), reasoning effort, and MCP access. Delivered as a shareable DSH agent preset (with bundled configuration plugins), not a standalone application.
Role-based AI swarms for DeepSeek Harness: an architect plans, parallel builders execute, reviewers gate quality, and an integrator ships. Per-role model pinning with fallback chains, review loops, evidence contracts, human-gated reviews, quota-aware pause/resume, and a live kanban + flow chart in the web GUI. 40 tests; installs from GitHub or npm.
Always-on AI teammate: hand it a recurring task in one sentence; dry-run rehearsal by default, snapshot before every real run, one-click rollback, CNY budget circuit-breaker, per-run cost transparency.
A long-form Chinese novel workbench inside DeepSeek Harness: read, edit and annotate the manuscript in place; AI reports problems with ready-to-adopt revision drafts, and the text changes only when you accept. A ledger for characters, facts and foreshadowing plus a world map keep a long novel consistent, and AI can continue, expand or rewrite chapters.
Workbench with an AI assistant, pause/stop controls, separate background-model settings, tasks/replies, Linky, scoped knowledge capture, local and Yunzhijia search, news reading and developer tools. Optional embeddings download a model. Yunzhijia needs its CLI/account; web chats need the desktop app.
Expose the running DeepSeek Harness Web GUI's authenticated URL as an agent tool (gui_auth_url), so browser automation can open the GUI instead of failing with 401. Install: dsh plugin --profile web add github:NingYuanLee/dsh-gui-auth-url
Role-based expert subagents for DeepSeek Harness with a task sidebar: explorer, librarian, oracle, designer and fixer delegate in parallel, each with its own model and reasoning depth.
Orchestration-mode preset generator for DSH: a lead agent delegates to four built-in role helpers that carry only their own tools, and the web panel adds or removes custom helpers with their own tools, skills, and models, per workspace — zero changes to the harness source.
Requirements interview before work starts: judges whether a request is clear, asks focused questions when it is not, in strict mode denies editing tools until the user confirms a four-part summary in chat, and keeps confirmed preferences in two-layer memory.
Two-level model circuit breaker with failover for DeepSeek Harness. When a model (or a whole provider) starts failing repeatedly, the plugin opens a circuit and routes the next model request to a configured fallback — no core changes, installable with dsh plugin.
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.
Turn a one-line requirement into verified delivery. TeamFlow runs a multi-stage pipeline — triage, PRD, design, technical plan, parallel development, QA with defect rework, acceptance — and gives the model 12 `teamflow_*` tools plus a workbench with a live pipeline graph and a backlog kanban. Each requirement gets its own folder holding the PRD, design, technical plan, QA report and acceptance record.
An always-on working style for DSH agents, packaged as an agent preset: restate the task, read before editing, verify each change with a real command, keep context lean. Ships 29 skills (plan loops, review loops, TDD, unsticking, PR watching) plus a turn guard that pushes back when a turn edits files without a successful check afterwards, and pushes back harder on a second miss.
Ports the pstack agent workflow system to dsh: 58 pstack skills, 23 playbooks, four native tools and five agent presets, with skill routing, role-based model configuration and role-routed subagents.
Blue-team defense mode for CTF and incident response: 37 defensive tools, MITRE ATT&CK coverage mapping, six worker roles, SQLite findings and tasks, an optional decoy server, deception/honeypot workflows, and a standalone console with full view.
A single-author novel-writing plugin for DeepSeek Harness: a subagent concurrency setting plus a complete novel-creation preset (persona). It is tuned for quantized small models — the tool catalog is slimmed and output behavior hardened — so you can run a full-length novel pipeline locally.
Windows-only guard against the desktop shell locking itself out: it counts the dsh-auth-* launch cookies the shell has accumulated, reports how much of the 16 KiB request-header budget they consume, and once the count passes 40 it backs up the whole Cookies database and lets DSH rebuild it, so every cookie in that profile is cleared. Install is one command: on load the plugin registers its own weekly scheduled task pointing at the scripts inside the package, and uninstalling it removes that task — nothing to copy into your home directory and no schtasks line to run by hand. The check itself runs while the app is closed (it waits up to 3 hours for the shell to exit). It does not raise the header budget or keep a floating panel; scripts/ can also be run standalone without the app installed.
A DeepSeek Harness plugin: dispatch work to DSH agents from Claude Code / Codex / Antigravity / Grok, without giving up the host's native subagent UI. Native Progress UI • Tier Policy & Escalation • Dispatch Guardrails • Jobs Board • In-Host DSH Sessions • Vision & Image Gen (Native-First) • One-Click Install
SpecWave (spec-wave@3.0.1) is a multi-host coding CLI — one declarative adapt table lands natively on 13 hosts (Cursor · Claude Code · optional DSH · agents · Copilot · Codex · Windsurf · Gemini CLI · opencode · Roo Code · Zed · Cline · aider) — with P0 gate / Harness process commands and IDE landing. Formerly SpecGate / dsh-coding-kit. Discipline assets remain ICVO (Inform · Constrain · Verify · Orchestrate).
Study workbench for exam prep and research: three-column task board with tags and filters, a spaced-repetition queue (simplified SM-2) that keeps finished cards coming back, a heatmap lit by actual focused minutes, weekly reports, per-day review notes, a pomodoro timer that survives panel switches, and Markdown export/import for Obsidian. Installable via dsh plugin add (dsh-study-desk on npm).
Trust pipeline for deepseek-harness plugins: deterministic static scan (11 rules) + LLM-driven audit protocol + two-part scorecard, with optional runtime guard (T1 sentinel / T2 fs & child_process hooks) and honeypot decoys. Monitor-and-alert only — vet never blocks or kills on its own.
A full-screen novel-writing workbench: chapter board, draft candidates reviewed and merged paragraph by paragraph, plot summaries carrying an index header, and a writing pack assembled from the outline, character cards and earlier chapters. It also reads a shelf of finished books you import, extracts their writing habits in one run, merges them into a single style standard, and puts that standard in the prompt for every later generation.
Cron task scheduler for DSH: on schedule, automatically creates a new session and injects your prompt as its first message, with task history and manual run/stop controls. Also runs KNJ workflows: pick files directly (stored as persistent snapshots, re-handed to the workflow on every fire) or reference them by path. Its panel is registered in the settings page (settings.section), so no separate menu plugin is required.
Cron/one-shot scheduled tasks: run shell commands or fire webhooks on a schedule, with optional ServerChan/DingTalk/Feishu/webhook delivery of results.
Role-based multi-agent team for DeepSeek Harness — your digital workforce. One goal assembles a team of product, architect, frontend, backend, reviewer and QA roles that deliver through a nine-phase gated pipeline, plus a persistent team you can keep directing across sessions. Zero runtime dependencies, no build step.
Scheduled tasks: run a prompt on cron schedules, each run opens a new agent session to do the work, with workspace binding, manual run, session auto-naming, and a fullscreen task management page.
Generate images from the agent on the user's own GPU by queueing a workflow on a local ComfyUI install over its HTTP API: Z-Image-Turbo for fast drafts and Qwen-Image-2.1 for final assets and legible in-image text. Registers comfyui_generate and comfyui_status plus a skill covering model selection and prompt craft, has no runtime dependencies, and starts ComfyUI headless when no server is listening.
dsh-qa · QA Workbench — A local software testing workbench plugin for DeepSeek Harness. Zero-dependency test project & iteration management with AI-assisted requirements, test cases, defects, milestones, reports, kanban and calendar.
Zotero skill for DeepSeek Harness: page-anchored Q&A, full-text translation and close reading, native highlights and Chinese notes, bilingual PDF and paragraph Markdown, evidence comparison tables, and reviews with citation tracking; finds papers on OpenAlex or Crossref, imports Chinese CNKI export files, classifies the library into research-direction folders, surfaces research gaps, and runs a ranked daily digest of new papers. Python-based (basic library management uses the standard library; the reading workflow downloads its PDF/OCR components on first use); writes need a one-time Zotero authorization, and daily scheduling is Windows-only. Adapted from the OpenAI MIT Zotero plugin.
为 DeepSeek Harness (DSH) 提供子 Agent 沟通增强与 Team 模型选择支持。 Flexible Agent Teams and model selection for DSH, with enhanced communication between parent and child conversations. 非官方社区插件 / Unofficial community plugin.
A self-evolving plugin for DeepSeek Harness (dsh). It observes how the agent runs, proposes improvements to its own assets via the LLM, validates each proposal inside a sandboxed trial agent, and applies only verified mutations — with a versioned ledger and automatic rollback on regression.
Build teams of independent AI agents inside DeepSeek Harness. Mix models and providers, assign one Leader, and let every member work in its own conversation while sharing the same Workspace.
Per-package automatic updates for the DeepSeek Harness plugins you choose. On a schedule it asks npm for the latest version of installed plugins, updates only the packages you check, and skips local link or file installs, pinned versions and packages with errors; upgrades stay inside the major version and skip prereleases by default. Updates go through the profile's own plugin manager, so the profile write lock, pnpm step, bundle-patch validation and hot reload are the host's, and a failed install puts the previous version back. Each cycle is appended to a JSON log.
Settings page for agent modes (presets): switch up to 15 capabilities per mode (commands, files or read-only files, web, subagents, and more) or individual plugin rows; edit each mode's system prompt with variable checks, a full preview, version history, optional live updates for running sessions, and an approval-gated mode_prompt chat tool; create modes from four starter templates or copies; merge built-in updates after a dsh upgrade while keeping your changes, and turn off rows that fail to load.
Runs one goal as parallel subtasks and merges the reports into one answer; the run survives a host restart, spending is capped, and the cost is printed. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
The root agent's context holds the plan and the decisions; reading, editing and running commands go to subagents that report back summaries. Subagents are full workers — they have write, edit and a shell — and the one thing none of them may leave behind is a process still running.
English: dsh-subagent-library is a named subagent roster plugin for the DeepSeek Harness Web GUI — manage role entries (model / persona / tool filter / depth / background mode) from a settings page, hot-reloaded, then let any conversation pick one with listsubagents and dispatch work with delegate. See README.en.md for the full English version.
Delay-send for the DSH chat composer: a clock button beside the send button schedules a message into the current session via 10-minute, 30-minute, 1-hour and 5-hour presets or an exact date and time, with the default continue prompt freely editable; delivery runs through DSH's official schedule automation tasks, so pending sends persist across restarts and can be reviewed or cancelled from the panel's pending list or the automation-tasks page, with a per-session badge count, a bounded safe-continue snippet plus the latest custom text, and a smart default time that pre-fills the GLM five-hour window end plus a two-minute margin when dsh-quota-watch is installed.
Design-review gate for DeepSeek Harness, a DSH port of Google's Elephant-Goldfish Model: a context-rich Elephant session drafts the design, then fresh, zero-context, read-only Goldfish reviewers stress-test it before implementation. Registers the `egm` plugin id; install one EGM bundle per profile.
An elephant writes the spec, a goldfish tears it apart, you decide — then code gets written. Adapted from google/elephant-goldfish-model (Apache-2.0). A verbatim mirror of the upstream material lives under vendor/egm/; the DSH adaptation is skills/egm-gate / egm-review, the skills/egm-classic- skeletons, and the dispatch mapping in lib/.
Sidebar todo list for DeepSeek Harness — grouped buckets, recurring tasks with weekday or month-day rules, a month-view calendar, and an agent tool that reads and writes the same JSON file.
Coordinate multiple live DSH sessions on a canvas with task planning, file cards, pipelines, and node-level progress.
QA pipeline as 10 agent skills: requirement analysis, test strategy, case writing and review, E2E (Playwright) and API automation, exploratory, regression scope and bug analysis, backed by a shared knowledge base with format rules, risk model and schema validators.
Todo plugin that records when each task is created and completed, with table, kanban, gantt and calendar views over the same data, categories, priority and type, @workspace-file links, JSON/CSV import and export, and a todo_time_log agent tool with /todo commands.
Sync team models, agent presets, and approved plugins into DeepSeek Harness, with team-scoped assistant operations.
Spec-Driven Development pipeline for Odoo: 15 tools take a request from an immutable spec through architecture to module code or live configuration, then require a persisted verdict backed by evidence from a real Odoo instance, with fail-closed gates, human-approved batches in a declared environment, Odoo's own CSV/Excel importer, and a journal that reverses the data written through the plugin.
Keep a DeepSeek Harness setup — skills, profile settings, AGENTS.md — in sync across computers through a private git repository. One codebase for macOS and Windows. 把 DeepSeek Harness 的配置(技能 / profile 设置 / AGENTS.md)通过一个私有 git 仓库在多台电脑之间同步。macOS 与 Windows 共用同一份代码。
A local task board with secretary, CEO, and historian roles, plus a desktop whale-girl companion for DeepSeek Harness.
A work assistant for WeChat: it records what you tell it into a SQLite task ledger, ranks items by urgency, reminds you on schedule, extracts people and their relations from your notes, and hands tasks to separate assistant sessions. Ships its own WeChat bot channel (scan to log in; private chat only) and a full-page dashboard.
Doubao video workshop: a gated pipeline from storyboard to finished cut. Locked art direction, shot validation, character-card vs reference-image separation, first/last-frame continuity and clip dedup; model-aware duration caps (Mini/Fast 10s, 2.0 15s, 2.5 40s). Uses ffmpeg for frame extraction, concatenation and subtitles; speech synthesis calls a separately installed local TTS plugin, and ASR subtitles need Python with faster-whisper.
A shared todo list for DeepSeek Harness: you and your agent manage the same tasks from a sidebar page or todo tools, with per-project and global todos, and one-click task references into the composer.
Deterministic step governance for DSH agents: rejects over-budget agent steps and denies risky tool executions before they run, with shadow mode by default and fail-open on errors.
Durable background child agents on the official subagent seam: start from any session, watch progress in the Web UI sidebar, message and interrupt any time, with per-child tool scoping, persona and delegation-depth caps.
LittleStar Meeting Room: bring AI sessions that cannot see each other into one room — for a meeting, or a game of werewolf. By 插件·2代小星辰 (LittleStar) and 辰启星明; the four-piece game layer (targeted visibility, private chat, concurrent asks, elimination) was contributed by 插件·3代小星辰. Any session can host — set the topic and goal, invite members in order, they speak one at a time, and the meeting closes with written minutes; it also runs games like werewolf. Includes 小白使用指南.md, a beginner guide written by 插件·3代小星辰.
Keeps a repository's task ledger as a resident prompt section with eleven native tools, plus a sidebar panel and a floating window for browsing the queue and signing off review tasks.
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.
Config-driven development-task orchestration for DSH: graph workflows (task/gateway/human nodes) with per-stage persistence, plus an in-editor AI assistant that configures workflows through conversation with live validation. Hand documents to nodes as generic attachments (no declaration needed): files land in the task workspace and ${inputs.附件} gives the newline-joined absolute paths, so a node parses them with its own prompt.
Adversarial review for DeepSeek Harness: put one settled plan on the stand, send read-only red-team experts at it by dimension, then split their findings into single defects you endorse or reject one by one. It never rewrites the plan and never fixes code.
Inject a personal rules file into the DeepSeek Harness system prompt, with silent-step and repeated-action loop guards; editable from the dsh settings dialog.
Read-only orchd panel for the DeepSeek Harness (DSH) right sidebar: open a project session and see that project's task board, dependency graph, ideas and review timeline next to the conversation. No project configuration — the plugin derives the project from the session.
A novel-writing workbench for DeepSeek Harness: you tap thumbs-up or thumbs-down on candidate passages, and the model distils them into a short preference profile that carries into later drafting calls while the manuscript stays out of the drafting context. Adds a chapter board, per-chapter writing packs, annotation-scoped revision that rewrites only the annotated paragraph and verifies the rest byte-for-byte, a project ledger, and local pacing checks.
Programming Mode agent preset bundle: the standard coding agent with its persona mandating the Superpowers discipline (skills first, brainstorming before building, plans before code, TDD, systematic debugging, verification before completion) plus an always-on Ponytail code-volume discipline (7-rung minimal-code ladder, default full); ships all twenty skills bundled (14 superpowers + 6 ponytail) and mechanically injects the full using-superpowers skill into every new session's first request.
Single-owner cloud tasks for DeepSeek Harness (大肥鱼 bot): submit from local chat or either IM bot, run continuously in a native cloud worker, and follow overall progress and artifacts in one workbench. Task permissions are independent of IM; includes agreed delivery and session archive recovery.
Evidence-gated acceptance for research reports: claims, citations, data scope and method limits each need a tick plus written evidence before a deliverable can pass, with same-artifact revision history and a standalone SHA-256 receipt that says when the bytes moved.
Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool drives the local deepseek-vision-cli browser automation (manual login helper, deep-think enabled, auto-closes browser) and returns image descriptions as text.
Aggregates every WorkBuddy account already signed in on this machine into one model pool, with manual and scheduled check-in, credits and expiry monitoring, per-model credit multipliers, and account switching with remaining credits right below the composer.
OTA guest-review reply ledger check: content and score, reply deadlines, responder, issue category and duplicate review ids.
Process management: brings ntd-style processes (multi-stage, multi-step agent workflow templates) into the dsh web UI — browse, edit, validate, import/export and AI-generate processes; the built-in library is read-only while the personal library is writable with live file sync, and agents read the library through process_* tools and advance work stage by stage.
Most n8n integrations have you paste a base URL and an API key into every conversation. This plugin makes n8n a first-class citizen of DeepSeek Harness: one settings page, one instance registry, and 21 agent tools that share it.
Community fork of l246804/dsh-pstack (cannot be installed alongside it: same plugin ids and tool names) that ports the pstack workflow system to dsh: 58 skills, five presets, a bundled script runner that works without node on PATH, a doctor for script prerequisites, and a translation layer for the remaining Cursor vocabulary.
Run your RunningHub ComfyUI workflows from DSH to generate images, video and audio, with a workflow setup panel, background tasks and multi-key management.
Sidebar footer badge that shows whether DeepSeek is inside a peak-pricing window right now: a state dot, the current multiplier (x2 during peak, 5 zhe / half price off-peak), a countdown to the next switch, and a 24-hour schedule bar whose white line marks the current time. Peak windows are 09:00-12:00 and 14:00-18:00 Beijing time; weekends and Chinese public holidays count as off-peak. The holiday table currently covers 2026 only. Client-only, no network requests.
DeepSeek Harness port of official pstack. Playbooks and principles are poteto's; only the harness call layer is rewritten.
Weekly retro for DSH: sessions, repeats, candidate skills and a five-tab insights UI, all local. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
Delivery workflow preset for DeepSeek Harness: an agent protocol plus seven tools that keep user requests verbatim, record feedback decisions, plan tasks with acceptance criteria, log real verification commands and exit codes, and write completion summaries as per-project JSONL files.
插件:自维护任务看板 —— 一张卡 = 一次真实 DSH 会话,跑完由人验收才算完成 · DSH plugin: a self-maintained task board where a card is a real DSH session and a human confirms completion.
Runs your kanban backlog during DeepSeek off-peak hours while the machine is idle: per-card git worktrees, evidence-gated completion, merge-back, and budget and idle gates. Linux or WSL only (needs bash, python3, git, jq, flock); initialise a git repo once with `npx dsh-offhours init`.
Requirement to a detailed design doc another AI can build from: the model fills a plan, the plugin validates it and emits a SPEC plus task cards, then independent review and implementation evidence check the result. Needs Python 3.11 or newer; the spec-graph engine it calls is bundled in the package.
Batch-parallel subagents for DeepSeek Harness: Swarm mode, per-item models, rate-limit recovery and a live in-chat panel. DeepSeek Harness 批量并行子 Agent 调度插件。
WeChat official account AI writing pipeline: six-step article runs (topic, outline, draft, gates, render, images) with a launch brief contract, a hot-topic board with per-item AI digests, RRULE scheduling to the draft box, a workbench UI plus chat tools and a /wewrite command, and fail-closed host approval before any draft-box push.
RETIRED 2026-10-05 — the official DeepSeek Harness now ships the Agent Teams subsystem (dsh-experimental-agent-team). Use native Agent Teams, or a better-adopted alternative such as @nanmicoder/dsh-agent-teams.
Webpage watch agent: keep a watchlist of URLs, snapshot each page on every sweep, detect changes by bigram-Dice ratio and keywords, log important ones and push to a WeChat webhook; agent tools page_watch_add/list/check/history/remove. Renders JS anti-bot WAF pages via the optional lexmount extractor.
Session-level autonomy gears for DSH: a rail on the edge of the conversation area switches P/R/NT/NC/NE/M-/M+/D/A and injects the active gear's behavioral prompt into every request; the model's set_gear tool can only downshift, and handbrake H blocks all tool calls. The set_gear tool can downshift on its own; upshifts need user approval.
Models+ settings page for the DSH web UI: per-model reasoning-effort tables, input modalities and compat flags saved through the official settings pipeline, with models.dev metadata prefill and API key management.
Consult multiple expert advisor models in a retro CRT chat-group card: one ask_advisors call runs an auto-deepen pipeline (driver deep-question, advisor relay, synthesis conclusion) with SSE streaming, 26 provider presets, a configurable daily quota, stop/resume, and optional advisor tool calling.
WeChat Mini Program dev loop for DeepSeek-Harness: check IDE status, launch the DevTools project, trigger preview and get the QR code straight into the conversation, parse compile errors into file/line/column, and watch it all from a sidebar panel. Six agent tools over the official DevTools CLI — honest about needing a one-time scan-login, never fakes a preview. Requires the Windows WeChat DevTools CLI and a one-time QR login.
Local SQLite taskboard as a native overlay page: projects, tasks, comments, relations, attachments and workflow automation, with backlog → todo → in_progress → in_review → done statuses, `taskboard_*` Agent tools that can only submit work to in_review, a headless JSON CLI and a packaged skill.
OpenSpec spec-driven workflows for DeepSeek Harness, generated from OpenSpec 1.14.3: twelve /opsx-* slash commands that carry the workflow prompt plus the arguments you type, and twelve openspec-* skills the model loads on its own.
Registers native doubao_generate_image and doubao_image_status Agent tools to automate Doubao Web (doubao.com) via Tabbit Browser, automatically extracting watermark-free 2.7K wm0 original images into local files and multimodal chat attachments.
AI-for-Science research workflow skill for DeepSeek Harness, aimed at researchers and grad students using agentic AI: multi-angle literature review with per-angle files, experiment design with a caveat list, figures and paper reading; each job returns files plus a cross-verification brief for a second model. Zero deps, MIT.
Session-local scheduled tasks: inject a prompt into the current session after a delay, at a fixed time, or on a repeating interval, so the model wakes up and runs it on time. Manage them from a panel above the composer, the /schedule command, or seven model-facing tools. Timers freeze while DSH is closed and never auto-resume; pause keeps the remaining time, so resuming continues from where it stopped.
Host-side progress checkpoints for long DSH tasks. After N minutes or M tool calls the model is nudged to post a one-line progress note and keep working, so you can correct it before it runs far off course.
Git commit-and-push automation for DSH with pre-push auditing, rule-based quality scoring, SSH key generation, and a three-tab settings sidebar.
AI-native iteration cycle: 24 anic_* tools and 77 HTTP routes that run evaluation, convergence gates, and auto-fix loops across projects, with a live white-box panel (interactive workflow graph, invocation feed, autonomy gauge, gate ledger, HITL queue) and an inline installable SKILL.md workflow kit.
Personal coding assistant that schedules, follows up on and verifies local Codex or Claude Code tasks from DSH, with WeChat, WeCom and Feishu remote channels.
Project document chain integrity check: stage order, completeness and amount parseability.
Personal assistant for DeepSeek Harness that turns conversational commitments into cross-session plans, reminders, and an auditable dashboard.
Installs a multi-agent novel-writing preset for DeepSeek Harness: one conductor agent dispatches five specialized subagents — world-building, plotting, character management, prose writing, and QA review.
dsh-cybernetics is a DSH plugin that explicitly designs LLM agent orchestration as a control loop: the session goal persists as an artifact of the agent's thinking; the task agent acts, the verify agent measures, the triage agent triages, the controller advances between rounds, and the user calibrates the outer loop through conversation — a negative-feedback loop of goal, action, measurement, and calibration.
Four GitHub workflow skills for PR triage, review feedback, GitHub Actions diagnosis, and safe draft-PR publishing, reusing existing DSH capabilities with gh/git fallbacks.
Runs one-time and recurring Agent tasks in fresh DSH sessions, with natural-language schedules, visual schedule editing and session-linked history. Supports custom models, skills, pause on failure, and permission settings.
Run your DSH agents like a company: departments, order dispatch, attempt credentials, an audit ledger and cost accounting on top of ctx.agents/subagents — plus a work board, an org chart and DAG task planning, no native team layer required.
Execution flow chart: renders the current session's execution as a vertical node flow (turns, user, assistant, tools, approvals, retries, compaction), appended in real time over SSE with auto-follow scrolling — the chart draws wherever the session executes.
A global personal to-do list that is independent of any session: sidebar panel plus an edge dock that peeks on hover and pops open when a task is due, with desktop notification and custom sounds.
Multi-agent workflow for math-modeling contests: the "UltraMath" preset runs a problem from reading through framework, derivation, coding, verification, paper and review, plus 4 single-stage role presets (mathematician, engineer, writer, reviewer) and 33 model-library skill docs.
Configurable image recognition for text-only DSH models: attached images are preserved through the DSH 0.1.7-rc.2 adapter pipeline, transcribed by an OpenAI-compatible vision model, and passed to the main model as text. Supports selectable OpenAI, Anthropic, Gemini or Azure auth headers and reports a missing API key before sending a request.
Defensive Agent Coding Workflow: Writer → deterministic runner → separate reviewer → human gate. The dacw_run tool writes, tests and audits code in an isolated workspace; nothing is merged without human review
Thinking-sorting plugin. A switch beside the composer puts the session into a three-stage mode — sort, critique, research — and each stage has a checklist of what it should produce before you press the advance button; finished ideas are filed by genre into Settings → Thoughts Center. A floating notebook holds half-formed sparks and opens a new session with the chosen one already written into the input box.
AgentTeams for DeepSeek Harness — an independent design branch of NanmiCoder/dsh-agent-teams; do not install both, since both register the same `agent-teams` row. Multi-agent team collaboration with a captain and members, tasks that carry dependencies, and messaging, all driven by natural language, plus a tree monitor in the web GUI.
Right-sidebar novel studio that treats a chapter as a pipeline with checkable artefacts instead of one long prompt: scaffold a project, inspect the exact context pack a chapter gets, generate 2-6 parallel candidates and keep the one you pick, then run chapters in sequence with per-chapter progress on disk so it survives an engine restart. Length band, cross-chapter Jaccard and drift ratio are enforced in code rather than by model self-grading; rejections come back as repair evidence for up to two rewrites. AI-fingerprint metrics are reported against a 3956-chapter human baseline but never block, because the distributions overlap. Ships 7 agent tools. The writing engine is a separate Python package that the plugin installs on first use. Needs Python 3.10+ on PATH (or a path set in the plugin settings).
dsh port of the shared handoff kit: handoff and task-id-bootstrap skills plus host-side automation — baseline state injection, per-turn snapshots with an Auto Log trail, task=<id> routing, continuation re-injection, a compaction guard with clear-required alerts, and read-only subagent handling — all writing the same .agents/state/ as the Codex, Claude, and pi editions for one-repo multi-agent handoff.
Scheduled wake-ups for the residents of a workspace. Each target — a "whale" — gets its own interval, quiet hours, daily cap, prompt and deny-list. Every wake-up reuses the same session, gathers what changed since last time, and sends one short prompt.
Discourages unnecessary sequential tool calls by guiding the model to batch ready, independent calls, potentially reducing wait time, model round trips, and token use when the runtime supports parallel execution; no scheduler changes.
RTS-style multi-agent orchestration board for DeepSeek Harness: issue plain-language strategic orders, a staff agent drafts acceptance-checked task orders, commander agents deploy typed subagent troops on isolated workspaces — with a 3D starfield campaign view, append-only event logs, and machine-checked verification.
Extends the composer model selector menu with a third Context window row, preset capacities (64K–2M), custom input, provider-wide sync, and adaptive compaction guard.
Daily auto check-in for MiniMax Code, WPS Lingxi, Baidu DuMate, AStudio, Qoder, Trae, Doubao, Huawei CodeArts and Tencent WorkBuddy: reads each app's own local credentials so nothing has to be pasted, supports multiple accounts per service, and lets you add any other site yourself by importing a JSON definition the agent wrote for it. Streak tracking, per-service schedules, collapsible sidebar cards. The Doubao service can also read its login cookies from the local Chrome, Edge, Brave or Doubao app cookie store (Doubao hosts only), and a custom service sends requests to whatever http(s) URL its JSON names.
Native workbench to select project sources, distill and test capability candidates, configure scoped Slack access, and review approvals and persistent tasks.
Manage agent-team roles in the dsh Web GUI: each role becomes its own selectable agent preset with per-role tool, skill and MCP switches.