Plugins

Offline-first UI/UX design intelligence library for DeepSeek Harness: design_recommend, design_review and design_search tools with a built-in database of 84 design styles, 192 color palettes, 74 font pairings, 99 UX guidelines, 25 chart types and 22 tech stacks, Chinese-first with zero runtime dependencies.

Turn your DSH token usage into a gacha game: feed a monster with tokens, earn coins, pull from 14 AI waifus (Kimi/GLM/Gemini/Claude and more), enhance artifacts, and build a Balatro-style battle team with daily sign-in bonuses.

Credential provider for DSH with password-protected AES-256-GCM storage, Argon2id key derivation (legacy scrypt v2 auto-upgrade), SHA3-256 integrity checks, and temporary runtime decryption.

dsh client bundle: a sidebar usage & cost dashboard — token stats, peak/off-peak aware per-model pricing, membership ladder, achievements and a daily heatmap.

Multi-provider wallet chip: official DeepSeek balance, per-session cost & tokens, third-party token totals, recharge shortcut, low-balance alerts.

Android companion bridge: QR-code LAN pairing with revocable device tokens and TLS fingerprints, a phone-connection and device-management panel, and an HTTPS access proxy serving sessions, live events and approvals to the paired native app.

Cost dashboard for DeepSeek Harness: aggregates model input/output/cache tokens across all local sessions, prices them with a builtin table (including DeepSeek peak/off-peak), and shows daily trends plus per-model and per-session tables.

A super-simplified LLM-wiki memory plugin: one index document (auto-loaded) + one markdown file per topic (read only when needed) — no dumping everything into the context and burning tokens. Simple and lightweight, painless to install/uninstall, and freely editable however you like.

Telegram duty gateway: phone-message task loop on a dedicated duty session, global approval forwarding with inline approve/reject buttons, telegram_ask choice questions, duty/local toggle with a web duty banner, zh/en messages, zero idle tokens.

Right-hand widget rail for the DSH Web UI: live session stats (turns, LLM/tool time, TTFT, speed, cache, tokens) and OpenCode Go quota via a same-origin host proxy; extensible widget registry for more platform usage widgets, visuals, utility actions and external integrations.

Lazy MCP gateway for DeepSeek Harness: one stable proxy tool instead of N tool schemas, servers connect on first use and idle out, metadata cached to disk.

Fills missing context window, max tokens, thinking levels, and image input on custom DSH models from models.dev, and lists unmatched models for manual edits.

DSH Desktop enhancement plugin: it puts verifiable facts on the table. Constraints are injected only when relevant, so idle chat costs no extra tokens; injection is layered (session-stable text in the system prompt, volatile content as a tail snapshot) and the prompt cache stays valid. Discipline: each turn is classified (question / research / discussion / diagnosis / execution) with boundaries enforced - no file edits on question turns, no unsolicited fixes on diagnosis turns; citing code lines not opened this session, negative claims about unseen symbols, requirements that do not match the deliverable, and dressing up “I did not check” as “waiting for your decision” are all called out; replies are written for humans - a code, field name or id must be explained in plain words the first time it appears. Memory and knowledge: 75%/90% context warnings plus an exported session recap (say "continue" in a new session); project knowledge accumulated across sessions by working directory, auto-captured and deletable by id. Inspectable artifacts: task contract / change record (auto-logged, unverified items flagged at delivery) / hypothesis record (conclusions must pass an evidence gate) / design decisions. Dashboard and personas: routing, trigger hits and block assembly are written to lume-metrics.jsonl and queryable via lume_metrics; personas are distilled from chat logs, novels, scripts or character sheets, with long-term and temporary memory, a memory star map and persona card export/import.

DeepSeek Harness plugin that aggressively saves tokens without affecting task quality: lossless head/tail truncation of tool results (default), grep-result folding, pressure-triggered dsh-compaction-basic delegation, and an LLM-summary CompactionEngine subclass for the aggressive mode. Saves 97.6% of input tokens on an 8-scenario synthetic suite, with all reductions routed through dsh event flow so model-visible = logged stays intact.

Live token stats under the DSH Web composer: streamed tokens/s, output token and first-byte latency, plus per-step estimate-vs-actual reconciliation using the official BPE tokenizer, to tell a slow stream from a stalled one.

Digimon-style raising game: hatch an egg that feeds on real work (turns, tool calls, errors) and evolves along four branching lines shaped by how you work; zero tokens, invisible to the model.

Expert manager: manage ntd-format experts and expert teams (plugin.json + Agent MD + skill sets), browse and install from a built-in market of 50+ experts, and run tasks in an expert persona via /expert-<name> without consuming model directory tokens.

Page-level UI generation for DeepSeek Harness: design tokens (theme.json) and code standards (code-style.json) drive a dsh-fuse fence that renders whole pages, with spec pre-validation, a theme contrast guard, a pixel-level style inspector (getComputedStyle), undo history, and a settings UI.

Auto-resumes interrupted DSH turns: sends a queued 「继续」 after turn/end with error, interrupted or max-tokens reasons, with a grace period, cooldown, exponential backoff, a consecutive-attempts cap, boot-time scanning, a settings card and a per-session stop/restore button in the composer toolbar; it never switches models or providers.

DeepSeek Harness plugin that turns UI screenshots into implementation-grade web specs using OCR, deterministic geometry, scene graphs, assets, and render comparison.

QQ 2007-inspired DSH Web skin: 72 native theme tokens, scoped three-pane chrome, original offline art and pixel buddy, an optional synthesized send chime, responsive/accessibility fallbacks, and reversible Settings switches.

Settings usage dashboard: tokens, requests, output tokens, and cache-hit rate from session logs, with a stacked chart and a breakdown table by provider, model, or workspace.

A faster, more efficient, and more accurate coding Agent preset. On 100 hard SWE-bench Pro tasks selected using multidimensional difficulty criteria, average elapsed time decreased by 36%, average input tokens per task decreased by 17%, and accuracy increased by 5 percentage points.