Plugins

DeepSeek Harness 用量看板：账户余额、Token 使用量、按缓存命中/未命中输入与输出的成本拆分，附一年活跃度热力图与分工作区趋势曲线。Fork of @lyk308/dsh-token-dashboard with dsh 0.2.0-rc.2 compatibility fixes.

Mobile web UI for DeepSeek Harness: a token-protected LAN server that lists all sessions, streams replies over SSE, and lets a phone continue any conversation; the desktop GUI shows a QR entry and, with dsh-whale-girl 0.3.0+, a phone held by the pet opens the same panel.

Replaces detected secrets (OpenAI, AWS, GitHub, PEM, Bearer) with deterministic, structurally valid honey tokens before they reach the model or the session file; adds manual marking for values the detectors miss, explicit user-visible restore, a cross-session canary alarm, and an opt-in JSONL log of substitution counts that never records the underlying values.

Pre-publish credential audit: walks a directory tree and flags API keys, tokens, private keys, database connection strings and hard-coded passwords before you commit, publish or ship. Zero dependencies, fully offline, findings are redacted to the first six characters.

Outbound route pool for DeepSeek Harness. Ships 15 seed routes plus a 20-entry candidate pool covering 7 target kinds (GitHub raw/codeload/main, npm registry, PyPI index, HuggingFace, general). Routes are verified before use: upstream IP lists go through a TLS handshake with full certificate-chain validation (a bare TCP check can be answered locally and report dead IPs as healthy), and failures advance a cooldown ladder of 2/5/15 minutes with the fastest healthy route picked per target kind. Routes are applied by rewriting the URL with one of four rules (prefix, registry, index, host-replace), reaching git, pip, npm, pnpm, gh, curl and wget through three paths: the shell seam (download commands the model runs through the bash tool are intercepted and rewritten automatically; commands wrapped by the pwsh tool, and fetches made by the host itself or the renderer, are not covered), two registered tools the model can call directly (line_pool_status, line_pool_run), and child-process spawn. Multi-line commands keep their line breaks and only the download segment is touched. URLs carrying credentials (user:token@host) are never rewritten, so tokens are not forwarded to third-party mirrors. No global config is modified. A sidebar panel lists every route with latency, failure reason and cooldown countdown, supports per-route retest and enable/disable, and shows live TUN/proxy status from network-adapter and loopback port checks. The candidate pool is re-verified every 24 hours so newly usable routes are added and dead ones dropped. 570 tests, 87% line coverage.

Shows what each installed skill costs in the model context and hides a skill from the catalog without deleting it. Lists every skill found on disk with the exact catalog line the model receives (description normalized and truncated at the catalog cap), its body size and token estimate; previews the catalog message byte-for-byte as the agent will receive it, compares that with the copy already published in the current session, and reports skills on disk that never reach the catalog (invalid frontmatter, or shadowed by a higher-priority root). Hiding writes disable-model-invocation into frontmatter and keeps the file, so the skill still works via /name. Also imports skills from ClawHub, Skills.sh and GitHub URLs and uninstalls user-owned ones.

Per-workspace gate that hides the tool schemas and system prompt sections of selected plugins from the model in directories that do not need them.

Frontend aesthetics engine as 17 native tools — a 118-palette evidence library matched by register, cross-register whole-page design directions, four mechanical gates (WCAG contrast, color-blind simulation, AI-slop detection, scorecard) with digest-bound verdicts, plus semantic design tokens, existing-page audit, CVD-checked chart palettes, CJK type scale, render-vs-tokens reconciliation and measured-numbers rationale. Fully local, zero network. Requires Python 3.8+.

Context observability and control for DeepSeek Harness: cross-session token analytics, session-level budget/prompt/tool controls, and optional agent scaffolds. It reuses the official tokenMeter, compaction, systemPrompt, and tools.restrict seams; monitoring is read-only.

Session-scoped checklists the agent maintains, with a tree per session, a token-budgeted prompt digest and a right-sidebar tab where item titles can be edited.

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.

Use your ChatGPT account to bring Codex models into DSH: choose models and thinking effort, chat with images, use tools and skills, approve local tasks, answer interactive questions, continue and compact long conversations, check quota and Token history, and maintain a supported Windows screenshot helper.

Manages a relay station's many groups and rates for DSH, switching the station's billing group in place and refreshing the model list and rate on stations that expose /v1/token/group; stations without it fall back to read-only and keep serving models.

Coastal light and dark palette for the DeepSeek Harness web GUI, built as a token-only ThemeRuntime overlay covering all 107 official alias tokens.

Browse, search, install, and apply VS Code color themes to the DeepSeek Harness Web UI: bundles 14 curated themes with live color-swatch previews, searches the official VS Code Marketplace for more, and one-click installs map any theme's palette onto the DSW design tokens with live switching and persisted selection.

Hello Kitty pink theme skin for the DSH Web UI: overrides the --dsw-alias-* semantic tokens in light and dark mode and paints a custom wallpaper on the app frame. Installs as a static profile plugin, so the theme restores automatically on every Harness start.

Firefly "Spring Missive" theme skin for the DeepSeek Harness web GUI. Overrides 74 --dsw-alias-* design tokens in matched light and dark sets, draws a spring-window backdrop with drifting petals and fireflies, places one character illustration on each side of the layout, and keeps the centre column legible with a radial spotlight scrim. Registers a Settings section with switches for the skin and for the artwork; both choices persist in localStorage.

Apple Liquid Glass skin that re-keys the harness design tokens, then adds its own settings page, a grouped model picker with peak and off-peak rate badges, and a merged usage panel.

Local token totals, per-model usage and a 12-week heatmap in a Chinese sidebar panel.

Free Egg credits panel for the DSH sidebar: WorkBuddy / Qoder account balances, daily budget, check-in state and per-turn spend (WorkBuddy credits priced per input / cache / output token type where rates are known), with one-click switching of the platform whose credits are spent first when new-api is configured. Requires a local WorkBuddy2API or Qoder gateway.

Live DeepSeek API balance and this session's token usage in the conversation header, with a detail panel for the topped-up / granted balance split, request count, input, output and cache-hit tokens, and context pressure. The API key is read on every query and is never cached, written to disk or returned to the browser.

A token toolbox for DSH: next-turn token forecast, a cross-session usage analytics panel built on the host session-projection unit, and prompt restructuring that writes back only when accepted.

Shows per-reply token usage, answer duration, and running session total under each reply.

Reorder configured models in the composer model picker, set cache-hit, cache-miss and output prices per million tokens, and estimate per-turn and session costs with built-in DeepSeek peak/off-peak rates.