DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。
456 个项目，匹配「mode」
hyqhyq3
MCP server manager plugin for DeepSeek Harness: Settings → MCP page, OAuth (PKCE + dynamic client registration) or static-token auth, tools registered as mcp__<name>__*
jiezeng2004-design
MCP bridge that lets ChatGPT create, view, continue, and control DeepSeek Harness (DSH) agent sessions.
jyh20030112
Dsh-visual-plugin.Give your text-only model eyes: forward user images to any OpenAI-compatible vision model and see the results in a Web UI right panel
rinDBeans
DeepSeek V4 Pro/Flash unified anchored agent preset for DeepSeek Harness (official API & opencode-go): two-stage RL-aligned bootstrap, model-aware path routing, epoch-aware long-session stability
songoao25
Bottom Info Bar — an information bar plugin for DeepSeek Harness: provider/model, live balance, peak/off-peak pricing with countdown, and real persisted per-session spend in a single line.
HuanLinOTO
模型生成时右下角弹出小游戏菜单（Wordle/消消乐/192 款参数化小游戏，可拓展注册表） | Pops up a mini-game menu while the model generates (Wordle/Match-3/192 parametric mini-games, extensible registry)
ai-shushu
Per-session quota meter for DSH: real-token billing, live progress bar, budget blocking, configurable multi-model pricing. 会话额度监控：真实记账、进度条、额度拦截、价目可配。
wingoo
Use local Codex App Server as a model provider in DeepSeek Harness
FeatherHunter
🎨 看腻了 DSH 默认皮肤？34 款 opencode 经典配色一键换上——tokyonight、dracula、gruvbox、matrix、rose-pine……即点即换，重启不丢。34 opencode themes for DeepSeek Harness, one click, persisted. More by @FeatherHunter: ⚡ dsh-prompt · 🧠 dsh-mattpocock-skills-deck
Hakunm
一款专为 DeepSeek Harness 设计的原生 Android 客户端，支持聊天、审批、工作区、文件及模型管理。A native Android client for DeepSeek Harness with chat, approvals, workspace, file, and model management.
juhe291
A corner HUD for DeepSeek Harness that shows your session's token pressure, per-model cost, and daily/monthly usage at a glance, with an editable budget and balance that tracks spending for you. 右下角常驻的 Token 仪表盘：实时看会话压力、按模型估算花费。预算和余额点一下就能改，每天每月用了多少都有记录。
AKS1st
统计各模型 tokens 消耗并估算费用，显示账户余额 | Model token usage stats and cost estimation with account balance for DSH
AtlasCloudAI
MCP server for Atlas Cloud - AI API aggregation platform for image/video generation and LLM
Cavan-Ou
Battle-tested multi-agent collaboration playbook for DeepSeek Harness: model-tier routing, spec discipline, git single-writer rule — as an installable skill. 多 agent 管线里运行 DSH 的实战协作规范
Flora233333
DSH 极简模式视觉辅助：保持灰测体验所需的首轮干净上下文，同时通过隐藏上下文和按需 Bash 工作流提供视觉分析 | Vision assistance for DSH minimal mode: preserve the clean first-turn context behind the gray-test DeepSeek experience while adding on-demand visual analysis through a hidden-context Bash workflow.
JuneLearn
让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度，并可为每次子 Agent 调用选择模型｜Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call
Letter2025
Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model
Pheobe-Southwood
dsh (DeepSeek Harness) ⇄ Paseo ACP integration bundle: auto-discovered model catalog, plan/execute modes, thinking levels, and native dsh slash commands in Paseo.
Scorp1o117
Vision model for DeepSeek Harness | DeepSeek Harness 外置视觉模型插件
Zhangbo-cn
Composer mic for DeepSeek Harness Web: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.
jiuge2467
现代化 DeepSeek Harness (DSH) 全栈增强工作台 · 多源 MCP 可视化调试中枢 · 视觉思考引擎 · 灵动极客伴侣
qwert702
Developer tool: live token usage & cost monitoring for DeepSeek Harness - consumed tokens for the current session and across all sessions, read from token-meter projections. No model calls.
sanshanya
Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (wire spellings) + request modalities (vision) for OpenAI-compatible providers. Settings section, zero runtime harness deps, no YAML.
sfyyy
On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model