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.
Install
via npm
Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.
The desktop app keeps its own profile, desktop, and only the dsh command it ships may change it — the npm-installed dsh refuses that profile. Install the command from the app menu (Manage dsh Command…), open Desktop once, quit it fully, run the line below, then reopen Desktop.
via npm
Resolves a published tarball rather than cloning the repository.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/desktop/pnpm-workspace.yaml.
Our install check ran in a web profile on npm's dsh, not in the desktop app.
What happened when we ran it
Installed cleanly when we ran it
Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 8d agoon DeepSeek Harness 0.2.2-rc.1.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
Security
No build script was blocked in our run.
Source: our sandbox install on DeepSeek Harness 0.2.2-rc.1, 8d ago.
package.json declares no preinstall, install or postinstall script.
Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.
shell commands (bash, exec, spawn …)
Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.
Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.
What it is — dsh-damage-pulse is a DeepSeek Harness plugin that tracks DeepSeek token usage, per-call and session costs, and account balance.
Who it is for — Users who use DeepSeek models in DeepSeek Harness for conversations need to know token usage and costs. Users who do not use DeepSeek models can consider it from a different perspective.
Watch out — Sandbox testing passed when installed in a fresh profile and registered with harness. It executes shell commands. No obvious issues found.
The verdict — I would install it because it tracks DeepSeek token usage in the DSH Web UI.
Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.
dsh-damage-pulse is a DeepSeek Harness plugin that tracks DeepSeek token usage, call and session costs, and account balance in the DeepSeek Harness Web UI. DeepSeek Harness receives completed model-call usage events, separates uncached input, cache reads, cache writes and output, and calculates charges from the provider, model, cache type and Beijing-time peak or off-peak period. Eligible calls are written to a local persistent usage ledger. The sessionId and sourceEventSeq pair prevents replayed events from being charged twice.
DeepSeek Harness also queries the official balance periodically, updates the displayed balance after charge events, and presents per-call details, session totals, historical summaries, peak/off-peak status and cache-aware animations. The plugin can apply editable provider/model pricing rules and can run third-party balance-query scripts.
This is intended for developers who need cost visibility across DeepSeek calls and sessions, including custom pricing or account-balance monitoring. It is a poor fit when the Web UI, local usage history or animated feedback is not wanted, or when balance access is unavailable. The plugin reaches the terminal surface to support configurable third-party balance-query scripts, so those scripts run with the permissions available to the agent environment.
The README documents an editable pricing panel rather than named configuration keys. Rules can be set per provider and model as either fixed pricing or peak/off-peak pricing. A rule can define separate rates for uncached input, cache reads, cache writes and output, with peak periods selected by time and weekday. Third-party providers can also supply a balance-query script. DeepSeek Harness uses the official pricing table by default; explicit custom pricing takes precedence over it, and pricing changes require restarting the plugin host.
The plugin can use a DeepSeek API key for balance queries. Missing credentials or a failed query leaves the local spending statistics available while the balance card reports that balance data is unavailable.
DeepSeek Harness records qualifying calls in a persistent local ledger and restores historical statistics and session summaries after restart. It shows call-level token and cost details, session totals, and global summaries for today, the last 7 days, the last 30 days and all history. The balance is calibrated every 60 seconds, while peak/off-peak status refreshes every 30 seconds.
The Web UI includes a draggable balance card, detailed usage filters, column settings, pagination, notification settings and module management. Five modules can be removed independently: desktop pet, data overview, notifications, pricing rules, and WeChat notifications. The update panel checks GitHub Releases and verifies the version, source, asset name and SHA-256 before installation.
Unknown or ineligible models do not receive the default price. Visual models use the usage data returned by DeepSeek rather than estimating image tokens. IPv6 and IPv4-mapped Fake-IP answers are unsupported for balance queries. The README does not name additional CLI commands, configuration keys, supported host versions or platform requirements. Configurable third-party balance-query scripts use the terminal surface and therefore inherit the agent environment’s permissions.
Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub
Same category
bowenliang123
DSH context insight panel: Context dashboard + /context command + Context browser — one-stop context lifecycle management with categorized composition, content details, evolution trends, compaction/injection events, and stats.
Installed cleanly when we ran it
Han-1413141
Per-session and daily API cost, budget with usage %, official balance, history dashboard, and one-click official price sync with peak/off-peak pricing.
Installed cleanly when we ran it
zh667
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.
Installed cleanly when we ran it
Ychris12138
Multi-provider usage dashboard with provider/model token breakdowns, calendar drill-downs, account balances, and OpenCode Go / Z.ai subscription quota tracking.
Installed cleanly when we ran it
Aisland-SJL
🌊 Persistent dock & fully-customizable balance/usage panel for DeepSeek Harness — activity heatmap, dual-channel comparison, local-only & privacy-first
Installed cleanly when we ran it
PolinniZhong
Personal center for DeepSeek Harness: cross-session usage statistics with per-provider and per-model breakdown (auto-discovers configured models), per-model cost estimation, global custom instructions, a data-driven desktop pet with bitmap & vector skins, and a conversation status overview, all local and offline.
Installed cleanly when we ran it
