Workflow & Automation

Native conversational image generation for DeepSeek Harness: ask the agent to create an image, and it handles generation and keeps the result directly in the conversation.

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.

Visible agent browser over CDP: 30+ bcdp_* automation tools, realtime SSE watch panel with direct click/scroll/IME input, element picking quoted into the composer as balanced @"picks/*.json" references, and human-verification notices.

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.

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.

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.

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.

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.

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.

Your AI learning companion: helping you plan your studies, understand concepts, and build projects to master a subject.

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.

Pre-visit due diligence and company research in DeepSeek Harness for customer background checks and risk briefs, with Qichacha MCP tool-call budget approval and entity confirmation.

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.

⭐ If you like this plugin, please star it on GitHub — it shows me that the plugin is useful to you and motivates me to keep developing it. 🐛 If you find a bug or would like to request a feature , open a GitHub issue in any language — I will review your proposal and implement useful suggestions in a future plugin version.

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.

Runs one-time and RFC 5545 recurring Agent tasks in fresh DSH sessions, with visual schedule editing and session-linked history.

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).

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

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.

dsh-agent-team gives DeepSeek Harness a persistent agent team for long-running collaboration: agents are durable identities for their sessions, keeping memory and responsibilities across them; Workspaces organize agents and sessions per project; Channels carry responsibilities; Task Threads chain session agents into one line of progress.

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).

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).

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.

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.

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.

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.

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48%，每题token减少45%，正确率甚至增加了10%。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 -48%, tokens per question -45%, and the accuracy rate even +10%.

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.

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.

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.

Integrates coding agent CLIs, persistent terminals and remote workspaces into the native DeepSeek Harness interface.

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.

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.

A governed swarm of six specialist DSH agents — orchestrator, planner, knowledge-base bridge, developer and two reviewers — turns a requirement into a strict phase pipeline where every delivery must prove itself with structured evidence before the next phase may start; reviewers are read-only, code merges only after a review pass, and an append-only event log gives full replay and audit on a live kanban board. Its design draws inspiration from the Hermes Agent kanban.

This repository is an installable release mirror for @kasenri/dsh-orbit 0.5.8. Canonical source: https://github.com/KasenRi/dsh-orbit-browser-plugins/tree/main/packages/orbit Do not develop features here; publish changes from the canonical source monorepo. Community plugin for DeepSeek Harness (DSH). Not affiliated with or endorsed by DeepSeek.

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

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.

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.

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.

Captain-led multi-agent teams that split a goal into tasks and dispatch them along an execution chain to members running in their own sub-sessions, each with its own model.

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.

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.

A collaborative kanban board where you and your AI agent plan, organize, and ship work together—without leaving DeepSeek Harness.

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.

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.

Agent preset bundle for wish and task management: create wishes or tasks from conversation, opportunity-day check-ins, micro-actions, plus a memory store and progress charts in the web UI.

DeepSeek Harness plugin that gives Codex read-only planning/review roles while DSH remains the sole executor. Two flows share the same workflow engine:

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.

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.

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.

A DeepSeek Harness (DSH) plugin that integrates RunningHub cloud ComfyUI workflows: a settings card for your API key and workflow library, eight runninghub tools for agents, a sha256 media upload cache, a local concurrency gate with FIFO queueing and timeouts, background tasks with completion notifications, and a durable task ledger with automatic restart recovery.

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.

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.

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.

Cron scheduler for agent tasks: create jobs by natural language or a sidebar UI, inject a user message into a new or fixed session on schedule to trigger a full agent turn, with run history, manual trigger, and live SSE sync. Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): injected messages declare the producer-owned source kind plugin:cron.

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.

Agent governance kingdom for DeepSeek Harness: territories, role bindings (bind/unbind/session with model/agent identity), and a plan→assign→execute→review task loop where Worker claims never auto-complete (Claim ≠ Fact), with a local GUI operations console.

Tender search and bid intelligence in DeepSeek Harness with proposed project search, rule screening, human review and Excel/PDF exports using user-authorized Qichacha MCP.

Token-cost pipeline for DeepSeek Harness: pressure-aware layered compaction (lossless projection below 40% context pressure, LLM summarization above), per-agent tool allowlisting, long-text-to-image with vision summarization, and a /token-status command tracking pressure, tiers, and saved tokens.

DSH web GUI scheduled-tasks panel: sidebar management of DSH and system (crontab) tasks with natural-language creation and execution logs

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.

Durable auto-research experiment loop for DeepSeek Harness, with create / run / monitor in the official Web GUI.

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.

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.

Claude Science-style research workbench: ReAct research-loop engine (research_* tools), versioned artifacts with provenance (artifact_* tools), and 10 science skills for genomics/pathogens/bioinformatics.

Personal assistant for DeepSeek Harness that turns conversational commitments into cross-session plans, reminders, and an auditable dashboard.

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.

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.

Runtime requirement drift guard that keeps long-running DSH agents aligned with the user's approved goal, constraints, and decisions.

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.

Host-neutral durable DAG workflows for Agents: CLI-native access, fixed MCP gateway, on-demand Skills, triggers, replay, and visual Canvas.

Local-first content production and operations workspace for DSH: manage ideas, scripts, media assets, schedules, goals, publishing status, and post-publication reviews.

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 sidebar entry is provided by dsh-knj-menu; install together: dsh plugin add dsh-scheduler dsh-knj-menu.

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.

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.

Turn an idea into a reviewable specification, implementation plan, task list, and resumable DeepSeek Harness goal.

Agent-driven kanban board: one board per workspace, per-task agent sessions, and a guarded human/agent workflow (Backlog → To Do → In Progress → Review → Done).

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)

Declarative task-DAG orchestration for DeepSeek Harness. This optional Cordis plugin registers a model-facing orchestratetasks tool, validates a bounded directed acyclic task graph before anything starts, and executes it through the existing ctx.workflowEngine.

Gitee/GitHub AI employee: @ the bot on an issue (Gitee or GitHub), it clones the repo, implements the fix on the branch you name, opens a PR to that branch, and can auto-merge and auto-close the issue. v1.2 adds security scanning: configure scan repos, audit with built-in/custom prompts, deduplicate, and file new findings as issues.

Mobile web shell for the DSH Web GUI: overlay drawers, draggable FAB, mobile composer fixes, and a floating image-upload button pinned above the composer (native gallery/camera, integrated with the validated add-images pipeline), zero desktop regression. Published on npm as dsh-webui-mobile.

Kimi-Code-style swarm: batch-parallel subagent dispatch with adaptive scheduling, a /swarm command, and in-chat live progress rows.

Novel-writing guardrails: 20 novel_* tools enforce fact-ledger consistency, phase and chapter gates, machine audit with deterministic metrics, and proposal-only revisions; a right-panel workbench covers reading, TTS playback, polish, proofread, continuity checks and batch drafting, and a bypass engine runs internal steps off the main conversation.

- GitHub Personal Access Token account management with secret-free summaries. - GitHub REST repository listing for github.com and GitHub Enterprise API URLs. - Local Git operations: clone, fast-forward pull, status, commit, push, and force-with-lease. - Sidebar panel with account, repository, local Git, and settings tabs. - Push and force push are disabled by default and are guarded on the Host side. - Token storage uses /.dsh/dsh-github.json with an atomic write and mode 0600. - Git HTTP authen

CoAligne is a collaboration platform where teammates and their Agents share project context. CoAligne Desktop syncs local project files and Agent conversations into a cloud project, and connects your local agents — including DSH — to that cloud context.

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.

Interactive canvas for visualizing Agent, Subagent, Workflow, Phase, and tool relationships in DSH Web.

dsh-chaos adds a local collaboration workspace to the official DSH Web UI. Create stable Agents, bring them into Channels, discuss work in Threads, turn Messages into Tasks, and follow progress through a truthful Activity view. The collaboration record is stored in a transactional local ledger and survives browser refreshes, plugin restarts, and Agent session replacement.

Dispatch subagents in DeepSeek Harness: pick model, reasoning effort, and tool scope per task; save common combos as named profiles for reuse. Built-in safety checks, cost estimation with savings analysis, and a full decision ledger.

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.

Drives the GME Test Agent from inside Harness: three tools list interface catalogs, start and repair autonomous test generation in a local Python backend, poll the task until review, and keep PR, skip and cleanup actions behind explicit user consent.

Drives the GME Test Agent from inside Harness: three tools list interface catalogs, start and repair autonomous test generation in a local Python backend, poll the task until review, and keep PR, skip and cleanup actions behind explicit user consent.

Ships a skill about handing work to subagents instead of doing it inline - which tasks are worth fanning out, how many to run at once, how to send them in parallel, and how to check what they returned instead of trusting the summary.

Model high-availability failover (quarantine, circuit breaking, probe recovery) and subagent orchestration (fanout/pipeline/supervisor) with bilingual settings UI.

A kanban board inside DeepSeek Harness, integrated with the conversation: the agent writes planning cards via kanban tools while you talk, boards are isolated per workspace (project), and data is persisted to disk.

PPT stage — presentation generation (Beamer/Quarto) from the paper for asset pricing and machine learning research. Ships one skill.

Schedules workspace Agent runs in fresh Result Sessions with persistent audit history, using a stock DSH Conversation tab or a global Shell page when its slots are available.

Verifiable issue-to-PR delivery chain: an 11-stage pipeline (analysis, search, code understanding, hypothesis, planning, implementation, patch ledger, tests, review, failure classification, PR build) with 4 human review gates, GitHub/GitLab/CodeArts credential connections, a 5-page workbench and a draggable AI assistant panel.

11 shareable workflow skills (handoff, triage, to-spec, to-tickets, wayfinder, teach, wait-what, dsh-mode-routing, ask-matt, overnight-execution, full-throttle) as an installable skill pack.

Reusable subagent definitions managed from a Settings page and dispatched through a single delegate_agent tool; ships with a built-in read-only Explorer preset and a nested-delegation policy toggle.

- 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) -

Interval heartbeat that wakes each root agent itself (followup injection) to proactively report progress, risks or blockers: busy-safe queuing, no stacking, auto-pauses when no human replies, re-arms on the next user message.

Automatically sends "continue" to recover from RATE_LIMIT (429) and QUOTA (insufficient_quota) errors. Per-session consecutive-failure counter (default 20, configurable 1-100), a toolbar on/off switch, and a settings-page card.

When a dsh turn gets interrupted — by a web restart or an upstream hiccup (rate limit, 5xx, quota error) — this plugin auto-injects a "continue" so your session picks up where it left off, with a dead-loop guard that hands back control if the retry produces nothing.

Loopback-first multi-agent message relay: HMAC-authenticated broker plus dsh plugin (relay_send/recv/peers/history), zero-dependency CLI and Python clients, wire protocol v1.0.

Cortex is a DeepSeek-Harness plugin that turns the host's primary (strong) model into a high-leverage supervisor. The supervisor plans, decomposes, verifies and accepts; routed executor models (small/cheap models such as Qwen3.8-9B) and tools do the heavy lifting. With a recursive task tree, dynamic routing, four-stage quality gates, budget control, failure recovery, policy reuse and per-dimension model evaluation, Cortex keeps quality stable while driving the unit cost of successful tasks down.

DeepSeek Harness plugin: first-class Git workflow tools for the model — repo status, diffs, commit creation with validated messages, recent history, and branches. No bare-shell git calls; every invocation is a shell-free execFile with path and message validation.

SpecWorkflow is a shareable workflow skill pack for DeepSeek Harness and other Agent Skills-compatible tools. It gives an agent a disciplined path from a rough request to requirements, an implementation spec, code execution, delivery review, repair planning, bug diagnosis, and source-backed research.

Policy-driven Git sync for DSH settings and profile configuration, with secret-aware projections, conflict review, and per-line apply controls.

Zero-credential Outlook automation: 13 tools that drive the local desktop Outlook client via COM — search/read mail, drafts, reply/forward, calendar, address book, rooms, free/busy — plus a sidebar new-mail badge. No Graph API registration, no SMTP passwords; anything that leaves the machine passes a three-layer human approval gate.

A DeepSeek Harness Web plugin that runs a user-defined command after the web profile has started successfully. 在 dsh web 启动成功后运行用户自定义命令的 DeepSeek Harness Web 插件。

Table of Contents - 🤖 Browser4 - 🌟 Introduction - ✨ Key Capabilities - 📦 Installation - Install DeepSeek Harness (DSH) - Install the Browser4 plugin (recommended) - Start DSH - Use Browser4 in DSH - Install browser4-cli (Optional) - Install-free usage (optional) - Quick Start - 🧭 Tool Selection Guide - How to Interact with a Page - How to Extract Data - How to Process at Scale - How to Turn HTML into Spreadsheets — Zero Tokens - 💡 CLI Guide for Humans - Quick start - Mental model - Global o

Claude Code style /init command for DeepSeek Harness (DSH): generates CLAUDE.md and symlinks AGENTS.md to it

Task Runner mode for DeepSeek Harness: the main agent decomposes large tasks into independent subtasks, dispatches them to subagents (default local model) in fresh short contexts, and synthesizes results; concurrency and worker/orchestrator models are configurable in the settings panel.

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.

一个 DeepSeek Harness 插件，帮助用户将功能想法和错误反馈整理为清晰、注重隐私的 GitHub Discussions。A DeepSeek Harness plugin that helps users turn ideas and bug reports into clear, privacy-aware GitHub Discussions.

Model-facing `generate_image` tool for text-only models: the model asks for a picture in natural language, Gemini draws it via the Antigravity CLI, the image is saved to a configurable output directory, and the tool returns the file paths for the model to use in its work.

Shut down Windows automatically after DeepSeek Harness tasks complete — a floating arm button plus a cancellable countdown banner (shutdown /a), zero runtime dependencies.

Multi-candidate mode for DeepSeek Harness (test-time scaling): floating panel config, the agent auto-runs parallel candidates plus verifier selection, scoped to the current session.

DeepSeek Harness plugin: Claude-Code-style lifecycle hooks for DSH. Configure shell commands that run automatically before/after model tool calls (pre-tool / post-tool) with a JSON payload on stdin; pre-tool non-zero exits block the call.

@cola1018/dsh-aicc-zhunao is a public DeepSeek Harness (DSH) preset for a main-brain workflow. It combines a delegation-first persona, a root-session execution gate, and a portable aicc-law skill for task boundaries, evidence, and safety checks.

A DeepSeek Harness plugin that periodically detects added, modified, and deleted files in a workspace and reports the changes.

Agent teams for DeepSeek Harness: named long-lived teammates over ctx.subagents, a shared task list, a member-to-member mailbox, virtual workspaces, and a live team room in the conversation view

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.

Model training stage — end-to-end analysis, model training, and estimation for asset pricing and machine learning research. Ships one skill.

Literature review stage — search, synthesis, and citation-chain tracking for asset pricing and machine learning research. Ships one skill.

Report stage — academic paper writing for asset pricing and machine learning research. Ships one skill.

Data stage — data discovery and quality assessment for asset pricing and machine learning research. Ships one skill.

A model-facing DSH plugin that starts a subagent on a model-selected LLM provider and model. The model picks the route (provider/model); the deployment owns the subagent backend (subagentProvider, default spawn), the default scheduling policy (backgroundMode), and the route allowlist (allowedProviders). Per-call scheduling is overridable with the optional runinbackground parameter, exactly like the official @deepseek-ai/dsh-tool-subagent tools. Later turns of a continuable child reuse the offici

Delivers a prompt to the current agent at a fixed interval — ideal for polling, PR babysitting, and build-fix-test cycles. Aligned with Claude Code's /loop semantics, multiple loops can run concurrently in a single session. Delivered as an official bundle plugin (dsh.bundle + dshClient channel), 0 patch.

This is not another generic news reader, arXiv search engine, or paper summarizer. It covers the missing path from a curated primary-source signal to a versioned release evidence bundle and then to an auditable reproduction decision. Executed attempts are retained—including failures and negative results—and a successful exact/scaled claim requires commands, artifacts, measured claim results, and independent verifier evidence.

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.

Gated four-stage video pipeline: brief, script, assets and compose, turning one sentence into a narrated explainer with ComfyUI workflows or image/video APIs and FFmpeg assembly.

Preset workflow template library: 12 reusable orchestration script templates with wf_template_list / wf_template_search / wf_template_run / wf_template_validate tools and static template validation.

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.

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.

Self-organizing multi-agent clusters with no orchestrator. Real DSH subagents coordinate through a shared append-only log that each agent reads and writes on its own schedule, with no topology and one dispatch per agent; a snapshot mode is also included where the harness freezes each neighbour view into the prompt and drives a ring/mesh/swarm cluster to convergence.

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.

Project board + landfill memory for DeepSeek Harness: sessions opened from a card auto-load the complete, latest project memory; persist by the rules, same-name detection, merge, per-group filing.

Checks each step of a plan before you approve it, using command rules plus Jev or an OpenAI-compatible endpoint with logprobs, and marks steps that can't be undone, affect things outside the workspace, weren't asked for or are too vague on the plan review card.

One-click launcher for DeepSeek Harness: detects whether the backend is running, starts dsh web if needed, waits until ready, then opens the main page in a new Chrome window. Ships a cross-platform CLI (dsh-launcher start / open / status / make-shortcut) and the harness_launch agent tool.

Cross-workspace worker fleets: one orchestrating session spawns named worker sessions in other project workspaces, queues or steers tasks into them, watches them in the background via a real host job, and collects their reports. Worker completions deliver themselves to the orchestrator's session rather than needing to be polled, so an idle orchestrator still reacts. Escalations and failed workers deliver by steer when the orchestrator is mid-turn and by queue when it is idle; a turn that ends without a report counts as a failure and the worker is replaced after a configurable limit. The roster persists to disk and each worker session carries a durable title, so a restart neither loses the fleet nor spawns duplicate sessions. Ships five agent presets at full plugin parity with the standard preset.

Unattended scheduled-jobs plugin for DeepSeek Harness (dsh): run agent tasks (spawn a one-shot agent to execute a prompt through the full dsh toolchain) or command tasks (run a script directly) on a cron expression, a fixed interval, or a one-time instant. Complementary to @deepseek-ai/dsh-schedule — that one is persistent in-session reminders, this one is a host-side job scheduler: jobs belong to no interactive session and fire automatically while the process is up.

Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and appends every decision to a JSONL audit log; ships in monitor-only mode.

Synchronizes DSH profiles and local plugin source archives through WebDAV and S3-compatible storage, with encrypted snapshots, conflict-aware recovery, and explicit self-updates.

An agent preset that turns a one-line idea into requirements, tech plan and maintenance baseline — every step is restated and confirmed by you before proceeding. No scenario presets: 73 atomic skills (6 master skills + a verify dispatcher + 66 sub-skills) load by context.

- omx question → askuserquestion（结构化逐轮提问） - Codex goal mode → DSH creategoal / getgoal / updategoal - 原生子代理角色路由 → subagent / subagentfork + 角色提示词 - tmux 团队编排 → workflow 工具 + 后台任务 - omx ralph CLI → DSH 原生 ralph 工具 - .omx/ 工作区约定（context / interviews / specs / plans）保留

Group-chat multi-agent orchestration console for DSH: autonomous decision-making, task dispatch, verification and iterative optimization for long tasks; bundles its own backend, installs with `dsh plugin add`.

Six engineering skills for Claude Code and DSH: research, architecture scouting, implementation orchestration, three-axis diff review, complexity audit and mutation testing. Skills delegate through the host’s generic subagent tools when available.

This repository is an installable release mirror for @kasenri/dsh-browser 0.1.0. Canonical source: https://github.com/KasenRi/dsh-orbit-browser-plugins/tree/main/packages/browser Do not develop features here; publish changes from the canonical source monorepo. Community plugin for DeepSeek Harness (DSH). Not affiliated with or endorsed by DeepSeek.

Embedded task management engine: decision-point protocol, idea capture wall, Linear-style issue store.

- 导出：扫描 /.dsh（profiles 配置、settings.yaml、.agent-presets、vendor/ link 目录）；硬排除 .credentials.yaml/.env/.pnpm-store/sessions/storages/nodemodules 等；settings/presets 做字段级凭据扫描 + 脱敏，处理明细进 manifest（secretReport） - 打包：单一 .dshmig（zip），内置 manifest（版本、平台、文件清单、sha256 校验和、link 映射） - 导入：预检（同 OS、dsh 版本、磁盘）→ 备份目标机 → 默认新建 profile（ -migrated，重名自动递增）→ link: 路径重算 → vendor/presets/settings 还原 → pnpm install → 验证链（链接解析 → dsh --dump-config）→ 失败自动回滚 - 验证链：L1 pnpm install / L2 link 解析（junction realpath）/ L3 dsh --dump-con

A declarative DeepSeek Harness agent preset for spec-driven development: Claude Code planning/review/distillation and Codex implementation/testing, coordinated through a Chinese persona and four static delegation tools. No custom Host code or browser UI is shipped.

Douyin local-promotion OEM ad daily/weekly report automation (Author: Kirin): collects 3 data sources (laike leads, plan-level delivery, video analysis) via a one-time Edge login, computes metrics, builds A4-style docx reports, supports free-choice scheduled run times and email notifications.

TeamsX for DeepSeek Harness — turn one session into a coordinated multi-agent team: a captain spawns durable member subagents, breaks a goal into a dependency-aware task DAG, and coordinates through direct mailbox messages, with a live all-SVG activity panel.

Let Codex dispatch tasks to DeepSeek Harness workspaces, follow execution, read results, and continue collaboration through a local bridge and companion Codex skill.

Web Bridge is an automation MCP server that uses a real browser. It gives agents a browser's eyes and hands: open web pages, read page structure, click, fill forms, take screenshots, and execute scripts. Its core mechanism is the accessibility-tree snapshot — rendering the page into a structured text tree with numbered interactive elements, so agents can interact with pages precisely without a vision model.

A gated math-modeling skill suite for DeepSeek Harness: a five-stage pipeline with stage gates, award-paper writing patterns, sensitivity analysis, statistical diagnosis, and a contest preset.

Round-table meetings for DeepSeek Harness 0.2.0-rc.2 on Windows desktop, reusing existing Agent sessions with discussion, editable task cards, sequential and parallel steps, shared meeting files, and secretary minutes.

Council of High Intelligence: assemble an 18-member think tank of historical figures for multi-perspective structured debate, with a live DAG side panel, SQLite run history, and per-project defaults via .council.yaml.

This plugin decomposes complex multi-step tasks with interdependent stages into an ordered set of independent execution units (domains). After human confirmation, each domain runs in sequence with automatic audit and output hand-off, keeping the entire process visible, traceable, and interruptible.

Multi-agent isolated debate for DeepSeek Harness: debaters of different temperaments research independently (no herding), then cross-examine, then judges converge to a conclusion. Runs as a background job with per-agent progress, token accounting, wave-parallel execution, and session-referenced resume.

AI can write resume text, but templates may still look wrong, pages may overflow, whitespace may remain, and small edits can destabilize the layout. dsh-resume provides an end-to-end DSH workflow for truthful content refinement, template selection, A4 layout tuning, visual review, and tailored resume versions for different job-search scenarios.

Intercepts turn-stopping to force one critique-and-improve round after each completed turn before the agent stops.

Proactive scheduling: an adaptive heartbeat plus a value network (urgency, relevance, interruption cost) decides when the agent should speak unprompted.

Compiles a rough need into a versioned task book (goal / context / constraints / acceptance / decisions / open gaps, all numbered) and hands it to any AI window losslessly: the receiver must pass a read-back handshake — restate, list gaps, declare READY — before work starts; /answer closes gaps with an automatic version bump, /forge-list tracks which window holds which version.

DSH plugin that auto-continues a native continuable subagent once when it ends with explicit max-tokens termination — then stops. No loops, no timers, official seams only.

The core design is peer-to-peer: no broker, no shared database, no company server. Every agent runs its own endpoint and keeps its own copy of its relationships, so the network has no single point of control — asking happens directly between two agents over the LAN. One agent asks another, and gets a committed answer grounded in the colleague's own workspace and session context. The result is a community of agents that discover each other, vouch for each other, and share expertise — with every r

Workflow tools for the local aflare binary: generate, validate and run local-first deterministic YAML workflow DAGs (WAL crash recovery, Saga compensation) through the local aflare binary, with 300+ templates built in.

Stages exact DSH tool calls without dispatch, presents complete canonical arguments in a durable Batch Review Inbox, invalidates approvals after edits or restarts, and commits only a matching SHA-256 digest plus single-use nonce through the normal DSH tool pipeline.

Delegate tasks to Google Antigravity CLI (agy) — a separate Gemini-powered coding agent on your machine — straight from DeepSeek Harness. No Gemini API key is involved: agy authenticates through your Antigravity login (system keyring / Google Sign-In).

Task reliability: auto-retry on model timeouts/failures, auto-continue unfinished tasks, completion verification, thinking-repeat interruption, resume after sleep or restart, autopilot mode and a remote trigger endpoint (npm: `dsh-task-reliability`).

Release status: QDD v0.1.0-rc.1 is the public submission-candidate line. This repository accepts reproducibility fixes, bug fixes, documentation improvements, and changes required by manuscript review. New research architectures are developed separately so this line remains a stable reference for the paper.

Turns each DSH workspace into a project: every new session auto-injects a project-workspace convention (read code before acting, empty folder means a brand-new project); a per-session Project toggle in the composer downgrades the session to a plain workspace with an explicit notice, with the state kept in the session log.

Task-list staleness guard for DeepSeek Harness: watches the session event stream and counts tool calls since the last todo_write; past a configurable threshold it appends one short notice before the next step, quoting the current list, so the model writes it back to the real progress instead of leaving a stale snapshot on screen. Pure prompt injection, no blocking and no data mutation.

Hook DeepSeek Harness into a Hermes pipeline: dispatch-spec template, model-tier routing, orchestrator-run quality gates, git single-writer rule, as a SKILL.md pack (bundle installable).

Kanban board for DSH: task state machine with git branch isolation, agent auto-execution, and review-driven merge.

Per-project scheduled prompts run as fresh headless agent sessions, with one-time, interval, and cron schedules plus durable run history.

Config-driven lifecycle hooks, including context injection: declare event, handler and outcome in YAML, where the handler is an in-harness tool (MCP included), a shell command or an HTTP endpoint, and the outcome is model-visible context, a denied tool call, or fire-and-forget.

Standalone DeepSeek Harness plugin. When the agent is ready with a plan, it opens the official Plannotator app — the real product, not a lookalike review screen in the chat.

Multi-agent validation for any repository: independent theses, adversarial critics, and a seal whose verdict is computed from real command exit codes — never from an agent's prose. One body, three runtimes: DeepSeek Harness, Claude Code, ZCode.

Superself's self CLI as model-facing tools (project context, work units, reports, decisions) plus a /self command — cross-session, cross-project project state kept outside the code repo.

Modular AI research/engineering skill pack, installable via dsh plugin add — registers 27 skills (security audit, paper reading/writing, figure drawing, dev workflow, storage analysis) on ctx.skills.

Synchronize the plugin-list configuration of DeepSeek Harness (DSH) clients through any S3-compatible object store — AWS S3, MinIO, RustFS, Cloudflare R2, Aliyun OSS (S3 gateway), etc.

Single-bundle reverse-engineering and pentest security plugin: first-turn tool narrowing, domain routing, and 33 tools covering APK, web, native binary, protocol, malware and LLM samples — with unpacking, license-bypass and anti-analysis case playbooks, an H-CoT evaluation engine (semantic routing, /hcot command), a web workbench with a ledger-driven tool shelf, an on-disk case workflow (auto-persisted evidence chain, E-numbered validated findings, post-compaction resume), GitHub-based external tool discovery, and 361 on-demand reference docs.

Long-form novel writing plugin: each book is a git repository of frontmatter files, with 39 DSH domain tools and a web writing UI. Deep import drafts candidates, AI adoption into canonical assets requires DSH approval, and deterministic continuity checks ship with a report-only benchmark. Independent open source (MIT), not an official DeepSeek product; requires Node >= 24.11.0 and currently targets DSH 0.1.2-rc.1.

Adaptive deep-research orchestrator plugin for DeepSeek Harness (official workflow engine, cybernetics/information-theory design)

DeepSeek Harness (DSH) 任务结果账本与验收插件：机械证据验收、默认零额外 token、数据本地持有。Local-first task outcome ledger & acceptance plugin: evidence-backed verification, zero extra model cost, user-owned sidecar data.

Git commit-and-push automation for DSH with pre-push auditing, rule-based quality scoring, SSH key generation, and a three-tab settings sidebar.

dsh-routines — scheduled agents for DSH: run a prompt on a cron, get the digest where you already are (file digests, chatnode delivery, unattended-safe)

When an agent is about to finish a turn while its session still has incomplete todos, the Host half injects a synthetic continuation:

Multi-role parallel argumentation for DeepSeek Harness: runs the real Codex and Claude CLIs in parallel, has the DSH model (Judge) write a third-party verdict back into the conversation, plus Obsidian-style single-agent direct chat and per-role model config.

Verification gate for DSH agents: every acceptance criterion must be backed by server-stamped real tool evidence before the completion gate lets a goal through (advisory audit, enforce gate, durable permits).

Self-evolution actuator: consumes problem tickets mined from session logs, synthesizes skill candidates (zero-code tiers by default) behind an eval gate with hold-out canaries, then promotes to project .dsh/skills with human confirm and deterministic rollback.

Enhanced subagent delegation tools for DeepSeek Harness (dsh): per-call model / provider / persona / toolFilter overrides, @preset: persona references, and provider/model composite model ids — shipped as a standard bundle that patches no official package file.

Two-phase agent preset for DeepSeek V4 Pro: the first request sees only bash+read (Minimal-aligned bootstrap), then the full Standard tool catalog after the first tool call or reply; ships as an installer bundle plus a manual preset directory.

Lowtide (as in low tide) runs task batches automatically in off-peak hours — a highly customizable task framework with four execution strategies, L1–L3 semi/full-auto adjudication, in-place task editing and preflight checks, built on the Cordis microkernel, one build for both desktop and web.