A DSH native integration for configuring per-model reasoning effort and subagent defaults in DSH, with README-backed installation and operating-boundary evidence.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-09-09
License
MIT
01What can it help you accomplish?
Use DeepSeek Harness for configuring per-model reasoning effort and subagent defaults in DSH.
The README-documented workflow and its resulting DSH configuration or workspace behavior.
DSH users evaluating dsh-thinking-effort before adding it to a profile or skills directory.
02How to install into DeepSeek Harness
Prerequisites
- Review the maintainer-stated compatibility and runtime requirements before installation.
Installation steps
- 01
Run the maintainer-documented install command: dsh plugin --profile <profile> add @hytime/dsh-thinking-effort
Verify the integration
- Check the documented activation signal: When the DSH Web runtime exposes `modelDirectories`, the client registers an optional `conversation.input.model` `seat` with a low `shadow` priority; it does not modify Composer itself. The slider
Rollback
- Use the maintainer-documented removal path: dsh plugin --profile <profile> remove @hytime/dsh-thinking-effort
03DSH integration and capability boundaries
README-documented DeepSeek Harness native integration.
README-documented DSH workflow
Review the maintainer-stated compatibility and runtime requirements before installation.→Provides the maintainer-documented workflow for configuring per-model reasoning effort and subagent defaults in DSH.
04Who is it for? When not to use it?
Good for
- DSH users evaluating dsh-thinking-effort before adding it to a profile or skills directory.
Not for
- Compatibility, credentials, permissions, or runtime requirements remain governed by the maintainer README and the target DSH environment.
05Compatibility, maintenance and safety notes
- Compatibility, credentials, permissions, or runtime requirements remain governed by the maintainer README and the target DSH environment.
MIT · maintainer README evidence
06Frequently asked questions
What does dsh-thinking-effort add to DSH?
It documents a DSH workflow for configuring per-model reasoning effort and subagent defaults in DSH.
How is it installed?
Follow the README command: dsh plugin --profile <profile> add @hytime/dsh-thinking-effort
What should be reviewed before use?
Check the stated compatibility, credentials, permissions, and runtime requirements in the README.
07Related DSH workflows
dsh-tui
by ccch1mneyyy
Claude Code 风格全屏终端 TUI：像素鲸鱼顶栏、双流光大字、实时工作状态行、思考流式展开、双击 Esc 时间回溯、上下文进度条 + TPS 仪表；接入 Agent preset（standard/code/minimal/cordis）、Skills、MCP、Goals、Todos、子代理，/ 命令注册表与随附技能（audit/bug/review/practice/pr_comments/release-notes/vuln-check）；纯插件挂载零核心改动。
dsh-better-sidebar
by omdsh-dev
Full sidebar workbench with file rendering and editing, terminal, Git, and subagents; third-party plugins can register new tabs.
dsh-tianshu-tui
by huiliyi37
DeepSeek Harness 交互式终端 UI 插件：会话工作区、图片端到端（剪贴板/视觉桥）、slash 下拉、审批卡片、推理可视化，纯展示层
dsh-damage-pulse
by wssfk12138
Game-style token-usage / balance damage-pulse visualization for DeepSeek/DSH.
08Data and sources
# dsh-thinking-effort
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-09. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.