dsh-ultracode
UltraCode agent preset for DeepSeek Harness 鈥?maximum-depth reasoning, plan 鈫?execute 鈫?verify, and parallel subagent orchestration, as a one-command-install mode.
304 results
UltraCode agent preset for DeepSeek Harness 鈥?maximum-depth reasoning, plan 鈫?execute 鈫?verify, and parallel subagent orchestration, as a one-command-install mode.
Import and verify DeepSeek Harness session exports with state sync, rollback protection, and an in-app workflow
Beautiful themed SVG flowchart tool bundle for DeepSeek Harness
DSH Web 任务面板插件:把需求、队列、子 agent 执行、自动复核、验收返工和定时执行做成一个可视化闭环。
DSH Web 三栏工作台:对话流只保留 AI 输出(工具调用/思考移入右侧面板),左侧工作区文件树带 git 状态徽标。Three-column workbench for the DSH web GUI: clean conversation flow, workspace file tree with git badges, and a live tool-call/think panel.
DSH web plugin: agent/subagent/workflow completion, approval-required, plan-review, goal-blocked, and user-question toasts with optional PushPlus push notifications
Solve the AI goldfish brain: a personal memory layer for DeepSeek Harness — preferences, project conventions, workflows, and error lessons, stored locally as auditable, evidence-backed Markdown/JSON. 解决 AI 金鱼脑:偏好、项目约定、工作方式与纠错教训的本地可审计记忆层。
Money math toolbox for DeepSeek Harness (dsh): loan payment with amortization schedule, compound growth projection, nominal/effective rate conversion, NPV/IRR/payback cash-flow analysis, and retirement withdrawal planning — zero runtime dependencies
CoAligne workflow skill installer for DeepSeek Harness; requires CoAligne Desktop (signed in) to provide the MCP connection the skill depends on
GitHub authentication and local Git workflow plugin for the dsh web GUI: accounts, repository browsing, clone, pull, push, status, commit, and a settings panel. Token is stored in ~/.dsh/dsh-github.json (0600, atomic write); push is disabled by default. Standalone Cordis plugin — mounted via cordis.patch.yml + a profile node_modules link, no dsh source changes.
Embedded Overleaf workbench tab for DeepSeek Harness Web: same-origin reverse proxy for self-hosted or public Overleaf (no X-Frame-Options limits), direct-CDP login with credential storage, selection quoting into the composer, agent-driven cursor insertion, and LaTeX workflow helpers
Fail-closed network recovery, recommended answers, and safe unattended continuation for DeepSeek Harness.
Add an "Open folder" entry to the workspace session row overflow (⋯) menu; opens the session's workspace folder with the host OS.
Workflow-net runtime for DeepSeek Harness: resource-aware concurrency, native loops and fan-out, static soundness checking before a plan becomes durable, and process mining over its own event log.
DeepSeek Harness plugin for organizing AI discussions into research topics, traceable knowledge cards, and reusable research materials on an interactive graph
Familiar-face commands, connectors flow, and the trust layer for DeepSeek Harness, delivered as one DSH plugin.
dsh 插件 · 工艺管理:把 ntd 的「工艺」(Process,多阶段·多环节 agent 工作流模板)接进 dsh web——浏览/编辑/校验/导入导出/AI 生成工艺,内置库只读、我的库可写,文件改动实时同步;agent 可通过 process_* 工具读工艺库、按工艺分阶段推进。
A visual decision workbench for DeepSeek Harness: explore ideas, focus branches, turn choices into execution graphs, and run them one node at a time.
Safety rail and state machine for GitHub stacked PR workflows in DeepSeek Harness
dsh「专家团」bundle:一句自然语言自动组建/持久化一支 12 角色多智能体团队,共享工作区协议 + 阶段门控编排 + 结构化交接 + 质量门禁/自动调度,实现者直接改代码并产出持久工件;带 live 团队浮层(质量门禁/覆盖率/工件预览)。 · Role-based multi-agent expert team for DeepSeek Harness: one sentence in, a staged and gated team delivery out.
DSH Web 对话滚动动效插件:自动跟随滚动平滑过渡(内容向上顶/向下拉的流畅滚动),边缘滚动物理回弹(小幅橡皮筋效果),手动滚动保持原生手感
Composer auto-hide on scroll for the dsh web GUI: the input bar follows the message flow off-screen when you scroll up to read context, and slides back in when you return to the latest message.
Visual plan mode for DeepSeek Harness: structured plan.json + plan.md, an editable React Flow canvas, comments, plan diff, versioned revisions, and reliable write-back to the agent.
DeepSeek Harness web GUI: collapse the agent trajectory (tool calls, thinking, workflow steps) while always keeping the agent's final output. A setting controls whether the trajectory is default-collapsed after the final output completes (default on).