Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

432 plugins found

A

dsh-official-reasoning-effort

ayowait/dsh-official-reasoning-effort

Official-style model + reasoning-effort control for the composer. Reuses the official picker and always offers Off/Low/High/Max — exactly like the official DeepSeek control — even when a gateway model declares no reasoning effort, with a small hint at the panel bottom when upstream does not natively support it.

023 days agoModels & ProvidersMIT
S

dsh-cot-translator-plus

sodapopper-pixel/dsh-cot-translator-plus

Reasoning translation for the DSH Web UI: template HTTP translation sites, or a model route through a Harness-registered provider or a custom OpenAI-compatible provider declared in the plugin.

019 days agoUI EnhancementsMIT
F

fanxi (dsh-nova)

fanxi1230/fanxi

A cosmic reasoning-effort slider for the DeepSeek Harness composer. Off, Low, High, and Max each have their own starfield and aurora, with smooth cross-fades and real per-session model selection.

022 days agoUI EnhancementsAGPL-3.0
A

dsh-prompt-forge

aliboder/dsh-prompt-forge

Composer prompt refinement: rewrite the draft through the harness LLM, preview the result, then apply or send it, with style presets, model-aware reasoning effort, cost estimate and a settings page.

021 days agoUI EnhancementsMIT
Z

dsh-effort-dial

zengxiaolou/dsh-effort-dial

Reasoning-effort slider for the DeepSeek Harness composer: drag through the thinking levels the current model declares and release to write the chosen level into the session. An auto band escalates one level after a tool error and another after two or more, and optional model routing picks a provider/model per task type.

023 days agoUI EnhancementsMIT
F

fanxi (dsh-reasoning-effort-dock)

fanxi1230/fanxi

Adds a draggable off / low / high / max reasoning-effort slider to the composer model row and applies the selected level to the current DSH session. The slider only appears for models that offer all four effort levels.

022 days agoUI EnhancementsAGPL-3.0
F

dsh-first-principles (plugin)

fengt8291-lab/dsh-first-principles

A machine-checked reasoning ledger: every fact must resolve to a real file:line and be quoted verbatim from it, every assumption must state what would falsify it, and a conclusion may not rest on an assumption that never comes back for review. The ledger can carry a review date, a confidence and a kill condition. Ships the checker tool, an /fp command family, an optional gate that asks before irreversible shell commands, and a web panel listing the error codes each round fixed.

026 days agoWorkflow & Automation
E

dsh-prompt-translation

epcn-fla/dsh-prompt-translation

Translates user prompts before sending and translates model reasoning and replies back into the user's language via translation APIs or configured DSH models, with independent content toggles and a composer menu.

03 days agoTools & CapabilitiesMIT
X

dsh-aux-degrade

xiamubumu/dsh-aux-degrade

Stops compaction summaries and session titles from burning their output budget on reasoning, by lowering the thinking level and raising the token floor for auxiliary calls only.

0last monthModels & ProvidersMIT
S

coding-plan

stli69/coding-plan

Volcengine Ark Coding Plan provider route for DeepSeek Harness with all 15 Coding Plan models and per-model reasoning-effort control, generated from a single source and drift-checked weekly.

0last monthModels & ProvidersMIT
S

dsh-plugin-team-subagent-control

sakana07x/dsh-plugin-team-subagent-control

Adds per-member model and reasoning-effort routing to DeepSeek Desktop Agent Teams, plus leader-initiated release of a teammate subagent run instance.

018 days agoModels & Providers
P

dsh-openai-oauth

pyh-pan/dsh-openai-oauth

Use ChatGPT subscriptions in DeepSeek Harness Desktop via official Sign in with ChatGPT, with dynamic Agent registration and native model and reasoning selection.

011 days agoModels & ProvidersMIT
H

dsh-reasoning-distill

huhu23333/dsh-reasoning-distill

Distill over-long model reasoning into its useful core, replay the compressed version on every later request, and report each session's cost and savings. Disabled by default: select one rewrite backend first. derive needs no install and works on packaged DSH; in-place needs 14 source patches and a rebuild (recommended for source checkouts); message-edit needs a third-party plugin and is experimental only.

023 days agoUsage & BillingMIT
A

dsh-codex-bridge

ak-blank/dsh-codex-bridge

Reads the local Codex CLI ChatGPT-plan quota (5-hour and weekly windows), defaults to gpt-6.1-sol at high reasoning, falls back to gpt-5.6-sol when a window has 10% or less left, and delegates tasks through codex exec with an explicit opt-in for the expensive gpt-6-astra model. Requires a signed-in Codex CLI (`codex login`).

027 days agoUsage & BillingMIT
Z

dsh-source-fold

zimeng-luo/dsh-source-fold

Replaces the composer model picker with a compact panel for provider-to-model navigation and an adaptive reasoning-effort slider, with a Default stop and no slider for models without adjustable efforts.

026 days agoUI EnhancementsMIT
L

dsh-context-window-picker

luyiheng1111/dsh-context-window-picker

Adds a session-scoped context window selector next to the reasoning-effort row in the DeepSeek Harness model popup: a pill showing the effective window opens a dropdown of presets below the model default, the choice applies to the next request of that session only, and a new session falls back to the profile default. It writes no config file and appends nothing to the session log.

028 days agoUI EnhancementsMIT
L

dsh-effort-dial

lushdawn/dsh-effort-dial

Codex-style reasoning-effort card for the composer: takes over the model selector and shows the current level, the model row and a segmented slider over the model's own adapter-provided levels, with a model list, a reset, and a purple aurora with twinkling particles at the maximum level.

029 days agoUI Enhancements
L

dsh-model-block-picker

liu19666/dsh-model-block-picker

Composer model selector grouped by provider: pick a provider card, then drill into that provider to choose a model, with cross-provider search and Reasoning Effort kept.

021 days agoUI EnhancementsMIT
L

dsh-claude-video-slider

ledas-as/dsh-claude-video-slider

Unofficial Claude UI-inspired model and reasoning-effort selector using the current model's available levels, with animated purple pixel effects.

06 days agoUI EnhancementsMIT
G

dsh-effort-picker

gorkaseto/dsh-effort-picker

Adds a sticky effort slider inside the composer model menu to select reasoning levels, with generic stops for custom models.

026 days agoUI EnhancementsApache-2.0
F

dsh-model-picker

faxble/dsh-model-picker

Model quick picker for DeepSeek Harness: a button left of the model dropdown opens a full model-selection dialog with provider grouping, live search, provider filter, capability tags read from the user's own input config, reasoning badges, recent-model shortcuts and a reasoning-effort picker; the choice writes back to the native dropdown immediately.

07 days agoUI EnhancementsMIT
A

dsh-output-loop-guard

adistancethereis/dsh-output-loop-guard

DSH guard against self-repetition in streamed model output: detects a degeneration loop in reasoning or visible text, aborts the runaway turn and wakes the agent with a corrective notice.

0last monthDev & Plugin ToolsMIT
O

dsh-harness-trace

oihai/dsh-harness-trace

Records every session as one readable Markdown timeline inside the session workspace - the full request sent to the model (system prompt and plugin injections included), user input, replies, reasoning, tool calls and results, file reads and writes, web searches, skill loads, command runs and token usage - with a review page, a per-session tab and configurable capture scope.

0last monthDev & Plugin ToolsMIT
D

dsh-launch-card

dingchenhui0618-arch/dsh-launch-card

Generates release material from what a local repository can actually support: a hero image, a feature grid and bilingual copy rendered as SVG and HTML from `README.md`, `package.json` and optional screenshots. Facts are quoted from those files — name, version, license, summary, features, install snippet — and a field that is missing is left unrendered rather than filled with placeholder text. Every feature carries a source citation such as `README.md#L42`, and a claim the repository cannot substantiate is linted out before anything is written, with the reasoning left in `lint-report.json`. `manifest.json` records a sha256 for each input and output, and `--now` or `SOURCE_DATE_EPOCH` makes a run byte-identical. Also ships a GUI panel that regenerates from inside a session.

020 days agoTools & CapabilitiesMIT