483 RESULTS · “dsh-plugin”
v1.2.1 · MIT
📖 Cross-agent research paper toolkit for Claude Code, Codex, OpenCode, and DeepSeek Harness—quick summaries, deep study materials, code demos, and a local web viewer.
v0.5.0-alpha.5 · MIT
Automatically turn successful DeepSeek Harness sessions into reusable, reviewable Agent Skills.
v8.0.0 · MIT
DeepSeek Harness plugin: 15 obra/superpowers engineering skills, bilingual descriptions, per-skill toggles | DeepSeek Harness 插件:15 个 obra/superpowers 工程纪律技能,技能描述中英双语自由切换,每一个技能本身自由开关
v0.2.60 · MIT
Mixture of Agents (MoA) plugin for DeepSeek Harness with /moa slash command
v0.3.25 · Apache-2.0
Prompt-injection, jailbreak, and secret-leak detection with allow/ask/block interception for DeepSeek Harness: an Aho-Corasick pattern engine and heuristics ported from the Prompt-Injection-Payloads, Jailbreak-Detector, and Secret-Key-Leaker-Detect assets
v0.21.3 · MIT
PTC 创造模式预设:PTC 全部能力 + 创造模式的 Cordis 工具集与编写技能。dsh 0.1.7+ 以声明式注册直接进入模式名录,旧宿主仍物化到用户预设根,双时代自适应。· A Creation-mode preset on top of PTC: the Cordis toolset and authoring skills. Declared straight onto the preset roster on dsh 0.1.7+; materialized into the user p
v0.13.0 · MIT
One-stop skills, subagent, MCP and LSP manager inside DeepSeek Harness (DSH), compatible with Claude Code, Codex, Cursor, Kimi and other agent plugin layouts.
v0.1.12 · MIT
Oh My Pi bash runtime ported as a deepseek-harness tool plugin: persistent shell session, output minimizer, managed background jobs, command interception
v0.1.0 · MIT
Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.
v1.9.7 · MIT
DSH 模型管理层:网关可达性探测、模型目录拉取、DeepSeek + MiniMax/智谱/Moonshot/StepFun 余额与配额、本月用量统计、余额预警、Provider 健康看板,再把本机装好的 codex / claude / agy 注册成子代理(装了才出现)。零运行时依赖,不改动 DSH 安装。
v0.2.6 · MIT
ACRYL - Agent Context Relay Yielding Lifecycles. One persistent workspace, one canonical context, any coding agent.
v0.6.8 · MIT
Manage your VPS from DeepSeek Harness over SSH: zero-token commands, an in-conversation terminal, AI tools with risk-tiered confirmation, and a recipe library. · 在 DSH 里通过 SSH 管理 VPS:不花 token 的命令、对话里的终端、按风险分级确认的 AI 工具、菜谱库。
v0.2.1-rc.2.4 · MIT
Use AI agents from the DSH session UI.
v0.25.4 · MIT
Evidence-backed UI delivery for coding agents working on existing Web products: declared criteria, criterion-bound artifacts, findings linked to declarations, and repair guidance. Evaluator review does not replace human semantic approval.
v0.2.21 · MIT
Codex coding preset with customizable prompts and tools for DSH.
v2.2.0 · Apache-2.0
AI 编译纯文本小说工作台 for the dsh web GUI: import a novel outline (docx/text), plan volumes & chapters with LLM, generate chapter by chapter (3000-4000 chars each), auto AI review & book audit, and export the full book as Markdown/TXT into your chosen output fold
v0.8.2 · MIT
dsh plugin: register locally-defined custom agents (~/.dsh/agents/*.md) as callable subagents via the use_agent tool, with continuable background dispatch and ask_agent follow-ups
— · MIT
A reliable coding agent for complex software engineering tasks.
v0.6.0 · MIT
VCP visual-synesthesia protocol plugin for DeepSeek Harness: render agent HTML output as real UI (cards / KaTeX math / Mermaid diagrams / built-in calligraphy fonts / zero-JS interactions), plug-and-play on any DSH environment
— · AGPL-3.0
RikkaHub fork,Android AI 客户端。支持 IM(类 Grok-Bot)模式,ChatGPT 订阅登录使用、跨应用划词悬浮翻译、高性能低延迟远程云电脑控制。
v0.1.22 · MIT
DSH session completion notifier: appends a plugin system message to the session log on turn/end and pushes browser notifications (Web Notification + toast) with custom per-reason image/icon/alert-sound, plus a fully customizable official settings panel (p
v0.2.33 · MIT
Core Goal Addon (Token Budget, Milestones, Git Snapshots & Retrospective Reports) for DeepSeek Harness
v0.23.1 · MIT
DSH 费用统计插件:会话费用行 + 成本归因报告,llm-pricing 动态价格。 / DSH cost attribution and usage dashboard, priced by llm-pricing.
v0.1.6 · MIT
Say goodbye to copy-pasting and DSH Token anxiety. Let ChatGPT on the web connect directly to your local project, code on its own, and hand complex tasks to DSH for sustained execution.