dsh-usage-card
Sidebar card that prices this session's tokens in RMB at official peak/off-peak rates and splits context share by source, with per-turn pricing and a Markdown/CSV history report.
侧栏常驻卡片:按 DeepSeek 官方价目(含峰谷与缓存差价)把本会话 token 折算成人民币,并按来源拆开上下文占比;逐轮计价,另附 Markdown/CSV 历史报告。
How to install
dsh plugin add github:Icstick/dsh-usage-card About
dsh-usage-card 侧栏「设置」按钮**正上方**的一张常驻小卡片:本会话的 token 用量、费用(RMB)、以及**按来源拆分的上下文占比**。 为 DeepSeek Harness(DSH)Web 界面设计。 默认(收起)——头部与四桶常显,占比明细收起: ┌─ 本会话用量 ─────────── 7.1M tok ¥0.55 ▸ ─┐ │ 输入未命中 96,266 输出 67,618 │ │ 缓存命中 6,955,648 命中率 99.0% │ ├────────────────────────────────────────────┤ │ 上下文占比 · 221k [估算 ▸] │ ├────────────────────────────────────────────┤ │ subagent 3 个 · 5,500 tok · ¥0.02 [实测] │ └────────────────────────────────────────────┘ 展开(点右上角 ▸ 或占比标题行)——逐项明细与收口两行: │ 上下文占比 · 221k [估算] │ │ ██████████████████████████████████████████ │ │ ● 系统提示 14.2% ¥0.04│ │ ● 工具 schema 0.2% <¥0.01│ │ ● 用户消息 0.…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-09-21
- Created
- 2026-09-18
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Related plugins
dsh-damage-pulse
wssfk12138/dsh-damage-pulse
Tracks DeepSeek token usage, per-call and session costs, and account balance with cache-aware charge animations in the DSH Web UI.
TokenLedger
zh667/TokenLedger
Sidebar usage panel that attributes tokens to the relay site that served each request, read from your existing provider config: today/month/all-time totals, per-site and per-model breakdowns, a year activity heatmap, and New API / Sub2API / DeepSeek balances.
dsh-usage-stats
Ychris12138/dsh-usage-stats
Multi-provider usage dashboard with provider/model token breakdowns, calendar drill-downs, account balances, and OpenCode Go / Z.ai subscription quota tracking.
dsh-personal-center
PolinniZhong/dsh-personal-center
Personal center for DeepSeek Harness: cross-session usage statistics, per-model cost estimation, global custom instructions, a global font-size adjuster, a data-driven desktop pet with bitmap & vector skins, and a conversation status overview, all local and offline.