DeepSeek Harness Plugin Hub

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All plugins

876 plugins
v1.0.0
dsh-billing-dashboard

Billing Dashboard

DeepSeek Harness Usage Dashboard (Permanent Plugin): account balance, today’s spending and token usage, a 7-day spending trend chart, one-click recharge access, and a fully Chinese interface.

models-usageui-customization20
Updated 8/24/2026
v0.0.1
dsh-usage-dashboard

Usage Dashboard

DeepSeek usage and billing panel for DeepSeek Harness: balance, peak/off-peak pricing, and live countdown.

models-usageui-customization20
Updated 8/24/2026
v0.1.0
dsh-token-pricing

Token Pricing

Per-model token pricing for the dsh web surface: durable USD rates with multi-window peak hours, a cost readout in the composer dock, and a collapsible draggable floating window with per-turn and per-model cost views

models-usageui-customization20
Updated 8/24/2026
v0.6.1
dsh-llm-cost

Llm Cost

Per-turn, per-step LLM cost metering for DeepSeek Harness: a costUsage session projection, a cost line under each message, and an LLM+web price auto-maintenance tool.

models-usage20
Updated 8/24/2026
v0.0.4
dsh-cost

Cost

DeepSeek Harness plugin: Tracks token usage and cache hit rate for each conversation round in the current topic, estimates costs based on official peak/off-peak prices and the time of each call, and displays the DeepSeek API balance.

models-usage20
Updated 8/24/2026
v0.1.2
@lengquan88/dsh-dual-auto

Dual Auto

Dual-model Auto routing plugin: flash low-cost direct responses / pro high-cost escalation + escape-learning feedback loop + persistent interoperability

models-usageagents-orchestration20
Updated 8/24/2026
v0.1.0
dsh-opencode-models

Opencode Models

Manage OpenCode Zen free-tier and Go-tier models in settings.yaml: live model listings from opencode.ai, configured-versus-live drift per route, add/remove through four agent tools plus an OpenCode Models settings section.

models-usage20
Updated 8/24/2026
v0.2.0
dsh-token-activity

Token Activity

DSH plugin dsh-token-activity

models-usage20
Updated 8/23/2026
v0.1.0
dsh-subscriptions

Subscriptions

DeepSeek Harness plugin: use your own Claude and ChatGPT/Codex subscriptions as model providers, over each vendor OAuth flow

models-usagesecurity-access20
Updated 8/23/2026
v0.3.0
dsh-provider-rate-limit

Provider Rate Limit

Per-provider & per-model rate limiting (token bucket, reject/queue modes) plus gateway identity rules for DeepSeek Harness

security-accessmodels-usage20
Updated 8/23/2026
v1.0.3
deepseek-cost-usage-status-plugin

Deepseek Cost Usage Status Plugin

Live DeepSeek API cost/usage/balance dashboard for the DeepSeek Harness (DSH) Web UI: a second composer stats line plus per-session cost tracking — shows on/off-peak (Beijing-time windows), session cost (official CNY pricing), ~¥/min burn rate, account balance, and current model. 在 DSH 内实时展示 DeepSee

models-usageui-customization20
Updated 8/23/2026
v0.1.1
dsh-token-anxiety

Token Anxiety

Token Anxiety widget for DeepSeek Harness: live per-task cost tracking over the session projection — peak/valley pricing, sortable cost table, currency manager (COP/USD/CNY + add/remove), click-to-explain, i18n

models-usageui-customization20
Updated 8/23/2026
v0.1.1
dsh-session-stats-panel

Session Stats Panel

DeepSeek Harness (cordis) client plugin: a right-side session stats panel showing average cache-hit rate, session cost, runtime, request count and cumulative tokens (DeepSeek pricing).

models-usageui-customization20
Updated 8/22/2026
v1.1.3
deepseek-balance-banner

Deepseek Balance Banner

DeepSeek balance banner for DSH: top-right USD/CNY balance chips with damage/gain animations and peak/valley detection

models-usageui-customization20
Updated 8/22/2026
v0.1.0
chicheng-peak

Chicheng Peak

DSH Peak/Off-Peak Reminder plugin: Based on DeepSeek’s official peak/off-peak pricing periods (peak: 09:00–12:00 / 14:00–18:00; all other times are off-peak), it renders orange (peak) / blue (off-peak) borders with breathing and flowing-light effects along the edges of web pages. It can also send re

models-usageui-customizationintegrations-communication20
Updated 8/22/2026
v0.3.2
dsh-provider-probe

Provider Probe

Safe, explicit provider connectivity and latency checks for DeepSeek Harness

models-usage20
Updated 8/22/2026
v0.1.2
dsh-concurrency-meter

Concurrency Meter

Read-only model request concurrency monitoring for DeepSeek Harness

models-usage20
Updated 8/22/2026
v0.1.2
dsh-error-lens

Error Lens

Read-only, redacted provider error diagnostics for DeepSeek Harness

models-usagedeveloper-tools20
Updated 8/22/2026
v0.1.0-rc.5
@deepseek-ai/dsh-model-catalog-xai

Model Catalog Xai

xAI and Grok Coding Plan LLM Provider model catalog plugin for DeepSeek Harness

models-usage20
Updated 8/22/2026
v1.0.1
dsh-cost-insights

Cost Insights

Auditable usage, cost, token, cache, balance and pricing analytics for DeepSeek Harness.

models-usage20
Updated 8/22/2026
v0.1.0
@zhourenke/dsh-agent-rate-limit

Agent Rate Limit

Agent loop rate limiter — prevents TPM/RPM limit violations by intercepting the LLM streaming pipeline and adding adaptive delays between requests

models-usage20
Updated 8/22/2026
v0.1.2
dsh-image-vision-bridge

Image Vision Bridge

DSH host plugin: automatically sends images in user messages to a vision model (default mimo-v2.5 on opencode-go) and feeds the returned text description to the main text model (e.g. deepseek-v4-pro), without touching the visible chat transcript.

vision-mediamodels-usage20
Updated 8/22/2026
v1.0.5
dsh-opencodego-quota

Opencodego Quota

OpenCode Go (opencode.ai/zen/go) quota usage plugin: keeps a quota card permanently in the DSH Web GUI left sidebar, displaying usage progress bars, converted amounts, reset times, and refresh times for three windows: daily (past 5 hours), weekly, and monthly; the automatic refresh interval can be f

models-usageui-customization20
Updated 8/21/2026
v0.1.0
luxueliu-usage-command

Luxueliu Usage Command

Luxueliu /usage command for DeepSeek Harness: per-day API spend card (by model × hour) from the local LiteLLM gateway log. Covers 3 billable model classes — official APIs (CNY + Beijing peak pricing), relay/OpenRouter APIs (USD), and plan pools (Cline/Token Plan, token-only) — all freely extensible

models-usage20
Updated 8/21/2026
v0.3.0
@abcdefu_cja/dsh-usage-stats

Usage Stats

DSH API usage statistics: tokens, requests, rounds, cache hits, cost estimates, and balances/quotas for multiple providers.

models-usage20
Updated 8/21/2026
v0.0.1
dsh-model-router

Model Router

Unified ModelID routing for DeepSeek Harness: one logical model id over multiple providers, first-token failover with cooldown, health-aware ranking, fallback reasoning efforts, purpose-based simple/complex task split, per-tier reasoning effort, and a settings-page management panel.

models-usage20
Updated 8/21/2026
v0.1.0
dsh-stats-hud

Stats Hud

Sci-fi HUD: turns the session stats line into game-style level bars, a speedometer and a rolling token counter.

ui-customizationmodels-usage20
Updated 8/21/2026
v0.1.1
dsh-workspace-hub

Workspace Hub

DSH workspace folders: categorize workspaces into folders in the left sidebar (drag reorder for folders/workspaces/sessions, inline edit, one-click expand/collapse, search) plus per-workspace token usage and cost stats (inline totals, hover detail card, overview panel with per-model price cards; Dee

productivity-workflowmodels-usage20
Updated 8/21/2026
v0.1.0
dsh-economizer

Economizer

Save tokens on the DeepSeek Harness (dsh) — on-demand tools / MCP / skills loading, cache-stable, with a v3 retrieval matcher. Works as an agent preset (picker-selected 「省钱模式」) or as a dsh.bundle (global, installable via `dsh plugin add`).

models-usageintegrations-communication20
Updated 8/21/2026
v1.4.4
dsh-quota-dashboard

Quota Dashboard

dsh-cost-meter 的 fork:会话费用/Token 缓存统计 + 统一额度看板(DeepSeek 余额 / OpenCode GO / Kimi For Coding / GLM Coding Plan / 火山方舟)。Fork of dsh-cost-meter with a unified multi-provider quota dashboard.

models-usageui-customization20
Updated 8/21/2026