DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Persona Select — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
P

dsh-persona-select

Persona Select

A plugin for DSH that injects system prompts and configured context, with the Whale Girl community persona built in. In this listing and the plugin settings interface, injecting system prompts is called “persona content,” while injecting configured context is called “conversation history.” Personas

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:gosutry/dsh-persona-select#0fdb649f0bcdc290c42c4fdad697515069358ff5
啥子鱼思考中文tok英文tok

Description

A plugin for DSH that injects system prompts and configured context, with the Whale Girl community persona built in. In this listing and the plugin settings interface, injecting system prompts is called “persona content,” while injecting configured context is called “conversation history.” Personas can be saved as presets in Persona Management in the settings interface. Saved persona content and conversation history can be exported as data blocks to PNG images or JSON files, with the PNG image itself used as the cover. The injection position of system prompts can be edited. The plugin can block system prompts, runtime context, schema tools, and other user-side content injected by dsh itself, ensuring that the model receives only the conversation content and has a tool keep-alive channel to prevent subsequent tool calls from producing only text. Conversation history can be imported directly from Session logs exported by DSH itself (/export), wrapped in a format that imitates DSH's own injection tags. Settings and personas are saved separately for each session; switching personas and changing setting checkboxes do not affect new or ongoing sessions.

Compatibility and provenance

Persona Select is published as dsh-persona-select and currently resolves to version 0.4.0-rc2. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
10/16/2026

Versions

0.4.0-rc2prerelease
10/16/2026

Related plugins

Loading related plugins…

Latest
0.4.0-rc2
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
10/16/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in memory-context.

Hindsight Coding Agents@vectorize-io/hindsight-coding-agentsReflect-only Hindsight long-term memory for coding agents (harness-pluggable: opencode, …), with automatic background ingestion (no setup CLI).Ab Memorydsh-ab-memory--- description: "The dsh-ab-memory package: a cross-session, file-backed agent memory with five tools (remember / recall / forget / load_skill / distill) and an always-on light injection." kind: "package-reference" ---Contextdsh-contextA DeepSeek Harness plugin for context insight and management, with context dashboard and context command, for understanding how the context is made of, and how it evolves.Memsearch Dsh@zilliz/memsearch-dshMemSearch plugin for DeepSeek Harness: shared markdown memory across agents, with capture, pre-step context injection, memory-recall skill, and a skill-candidate review panel.