better-model-provider
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.
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。
25 个项目,匹配「request」
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.
Yunado
DeepSeek Harness QoL plugin for the local Qwen3.8 line (27B/Flash-Next): per-request thinking budgets, a compaction backend that stops burning the output cap on thinking, and a settings tab. 本地 Qwen3.8 线的 DSH QoL 插件:逐请求 thinking 预算、不再把输出帽烧在 thinking 上的压缩后端、设置 tab。
kvmem
DSH SuperAdvisor: on-demand second opinions from a stronger model, with editable requests and per-call human approval.
Letter2025
Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model
ruler770525
Anchored-standard agent preset for DeepSeek Harness: Minimal-aligned first request, low-injection post-promotion, indirect AGENTS.md loading — anchored intelligence without the IQ drop. (DeepSeek Harness 的锚定标准预设:首轮 Minimal 对齐、晋升后低注入、AGENTS.md 间接按需加载——锚定智力不降智。)
LucienLL
Global proxy for DeepSeek Harness: route agent tools, model requests and web fetches through the Windows system proxy or a custom proxy with one persistent toggle and agent-visible status
Howardzhangdqs
DSH recap plugin: distills every model request (turn:step) into one sentence, rendered inline in the conversation flow
Letter2025
Two-level model circuit breaker with failover for DeepSeek Harness: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback
sunyuhuirong
DeepSeek Harness plugin: conversation history request rail (ZCode-style) - 会话历史请求迷你滑轨
6-debug-6
A simple popup that can quickly show when Deepseek has finished thinking or is requesting permission during split-screen.
xulelenlp
dsh-web-artifact-designer 把「帮我做个海报 / 网页 / 信息图 / 图表」变成一份可直接双击打开、视觉上真正像样的自包含 HTML / SVG 设计稿。 A DeepSeek Harness (DSH) skill that turns visual/frontend design requests into polished, self-contained HTML/SVG artifacts — instead of generic AI-looking pages.
zhangzujian
DSH compatibility plugin for redundant same-mode sandbox escalation requests
Xidong-AI
A proactive rate limiter plugin for DeepSeek Harness.
Shyboy0499
DeepSeek Harness plugin: reports what changed in your authored pull requests since your last check — merged, closed, or gone stale.
a1113622001
DeepSeek Harness client plugin: right-side session stats panel - cache hit rate, session cost (DeepSeek official peak/off-peak pricing), account balance, runtime, request count, cumulative tokens.
gao-gao-zai
Native DSH HTTP request plugin with configurable credential whitelist and usage skill
lim12137
Extra model-request recovery for DeepSeek Harness: retries PI_AI_ERROR failures once after a fixed 20s delay; other error codes keep the built-in dsh-llm-retry exponential backoff.
qingfengyu153781-star
Native Windows popup dialogs for DeepSeek Harness (DSH) approval requests + turn-finished notifications
NecromanAlbert
Any DSH session can request a Desktop restart, then the same persisted session is resumed and followup'd with its mission.
SipengXie2024
User-attention notifications for DeepSeek Harness (dsh) web: turn end, approval requests, and model questions — in-page toast + OS-level browser notification
cking000bigdemon
Eight DeepSeek Harness plugins: persona, language guard, per-request vision fallback, python/windows write guards, cross-agent memory, image generation, and skill shell injection.
dsh-plugins
Rewrites the User-Agent sent by every outgoing HTTP request (LLM API calls and other global-fetch traffic) to a value of your choice, configured live from a dedicated UA 设置 (User-Agent) tab in the Web settings. 为 dsh 发出的所有出站 HTTP 请求(LLM API 调用等走全局 fetch 的流量)改写 User-Agent,并可在 Web 设置的 UA 设置 选项卡中实时配置。
duanyunlun
Per-provider request headers in the DeepSeek Harness Models settings page, with per-conversation ${sessionId} expansion.
n0pe-sled
dsh plugin: keep injected runtime context and skill context as user-role turns before the human request