Plugins

Quadro de foco para agentes do DeepSeek Harness: notas duráveis mantidas pelo modelo no workspace da sessão que fixam o objetivo, as restrições e as decisões ao longo de compactações e sessões, com injeção automática de contexto, arquivamento ao limpar e um painel web opcional.

Endurance-coaching skill bundle that defaults to Intervals.icu for training data (activities, intervals, streams, training load, HRV, resting heart rate, sleep in-bed hours, eFTP) and uses COROS only for training-plan read/write and for fields Intervals.icu lacks (sleep score, recovery score), with iGPSPORT as a fallback for ride details. It turns that data into readiness gating, VDOT pace and heart-rate zones, periodized weekly plans, session reviews, race-day pacing and fueling, and weather-adjusted workouts. The bundle registers the endurance-coach skill in the profile, ships deterministic helper scripts, reads an athlete profile created by its init script, and requires the agent to state when data is unavailable instead of inventing it. Data comes through separately installed MCP servers — the Intervals.icu MCP server for training data, the dsh-coros plugin for training-plan read/write and sleep/recovery scores, an iGPSPORT MCP server only as a ride-detail fallback — and its bundled scripts need Python 3.10+; with none of them it works only from numbers you type in.

Bridges the official COROS MCP server into DeepSeek Harness with a self-contained local stdio-to-HTTP bridge and on-device OAuth login, exposing 34 COROS tools on the current endpoint for sleep, HRV, resting heart rate, recovery, training load, activities and FIT files, plus workout and training-plan CRUD and scheduling.

Five-layer persona (L1–L5), event memory with FTS5 plus Dice retrieval, cognitive filter, skill cards with auto-frozen asset packs, millisecond reflex rules, three-tier safety degradation, a read-only brain star map, and an optional VPet-Simulator MOD bridge.

Nine single-ink print palettes — sage linen, kraft paper, lead type, cyanotype, risograph, CRT tube, phosphor screen, punch card, floppy disk. Each palette carries its own paper grain, type pairing, corner shape, section rule and a whale mark redrawn in its ink, plus a letterpress pass (paper tooth, sheet mottle, ink bite) that can be switched off. Every palette ships separate light and dark tokens.

JetBrains IDE bridge for DeepSeek Harness on Windows: installs as a DSH bundle, publishes the authenticated DSH URL, registers the open IDE project, relays the IDE MCP server, and serves a compact tool-window panel with streaming, approvals, Plan/Act, steer sending, session switching and archived-session filtering. The matching IDEA plugin is attached to the same release; your DSH agent can install it.

Autonomous product-polish loop skill: every round opens a fresh brainstorm from 3 forced perspectives, picks one small angle capped at ≤3 files and ≈100 lines, implements it, verifies with the repo's own tests, build or lint, and commits it as a single round commit; the round is logged to a per-project ledger, and ideas too big for one round go to an icebox. A red check ships nothing — the round commit is reverted immediately so the failed diff stays in history. Non-git targets are rejected before any work starts. Pure skill bundle: no MCP server, no runtime dependencies. Requires DSH 0.2.1-rc.2 or newer, below 0.3.0.

Zhinao (second brain) for DeepSeek Harness: Markdown-authoritative layered memory (L1 long-term model gated by user confirmation / L2 knowledge with mandatory sources / L3 recent status under daily quotas), a local recall ledger explaining every injection, lifecycle engine with weekly review and a Web panel. First-run wizard initializes a blank brain, adopts an existing Zhinao directory read-only, or fills in only missing skeleton files; existing files are never touched.

One click beside the composer turns a half-formed draft into a structured prompt the AI can act on: goal, constraints, output format and acceptance criteria filled in, placeholders only where a real decision is missing. Rewritten in place and never sent — undo with one click or Ctrl+Z. Four editable presets (general / code / writing / translation), optional conversation context to resolve references, and a model that either follows the session or is pinned to a chosen provider and reasoning effort. Requests survive session switches and typing while a rewrite is in flight; a result that no longer matches the draft is kept for retry instead of overwriting it. Pure JS, no build, no bundled dependencies.

Local LoRA and QLoRA fine-tuning in a panel: import JSONL, see a VRAM estimate before training starts, evaluate, and export an adapter. One-click Python venv setup, but you must supply your own Python 3.10+ and an NVIDIA GPU (6 GB or more). Verified end to end on Windows 11 with an RTX 3060 6 GB; the installer refuses non-Windows hosts, so Linux, macOS and other GPUs are unsupported for now.

Global cyber-terminal theme: a click-through full-screen Matrix code-rain overlay, phosphor-green UI styling, a sidebar one-click toggle, and adjustable speed, density, opacity and glow with three palettes.

ADHD-friendly focus soundscape docked under the DSH composer: five procedurally synthesised noise colours (white, pink, brown, rain, fan), a live-waveform orb, a 15-90 minute fade-out timer and a liquid-glass popover. No audio assets and no network requests.

内置 zk 的 DSH 知识库 / 日记插件：装好即用 —— 自动装 zk、建笔记本，给 agent 一组 zk_* 工具（搜索、读写、日记、双链），设置页里管路径、索引与自检。

Matrix-style binary (0/1) digital rain for the Harness interface: columns spawn only while a task is running, fall off screen when it stops, and leave a blank canvas; frosted-glass token layer with adjustable digit and panel opacity.

COROS Sport panel for DeepSeek Harness: sign in to COROS inside the panel, read the account, bound devices, recovery, fitness, recent workouts, daily health and the training schedule in one dashboard, and get a plan from the model with /coros-plan. The plan page writes a fixed four-week, 16-session plan to the account only after a two-step confirmation.

Injetor de inicialização Lingshu: executa brain.py startup a cada nova sessão de agente e insere persona, memória e tarefas automaticamente. Requer Python 3 e a habilidade Lingshu instalada em ~/.dsh/skills/lingshu; se faltar qualquer um, não faz nada em silêncio. O repositório principal também inclui um ponto de entrada SKILL.md no bundle.

Capacete para programação com IA: gradua gravações (L0 somente leitura / L1 somente workspace / L2 total) e isola edições privilegiadas. Abaixo do nível necessário, recusa a gravação e devolve um bloco pronto para colar. Todo caminho passa por verificação raw-string de traversal e realpath, que também detecta escapes por junction.

Destila conversas diárias em um cartão de personagem atualizável e um módulo emocional entre sessões que treina a persona.

Três skins retrofuturistas para a DSH Web GUI: trem ao anoitecer, chuva neon e costa ao pôr do sol; seletor na página e escolha salva localmente.

Cria backups frios offline de um perfil DSH do Windows e dados Home selecionados; permite inspecionar ZIPs separadamente e restaurá-los com um assistente WPF independente para um novo destino com runtime compatível comprovado.

Adiciona reações de stickers e emojis ao chat Web/Desktop do DeepSeek Harness: seletor no compositor, stickers do agente renderizados como imagens enquanto a transcrição mantém a tag do pacote, reações abaixo do balão do usuário e efeito de chuva de emojis.

Tema retrô de fósforo CRT: telas Matrix verde sobre preto puro, verde-âmbar 40K ou âmbar TFEL, com texto brilhante em negrito, animação inicial de chuva de código e painel de controle estilo BIOS.

Dez fundos animados em tela cheia para o painel de conversa DSH — céu estrelado, chuva de código, circuitos, luta de espada, gato, garota, caça, corrida, neve e bolhas —; um tema aleatório por turno e uma camada sobre a coluna de texto para manter a leitura.

Audita o que a compactação de contexto realmente perdeu. Lê o log bruto de eventos e verifica se as restrições permanentes do usuário (não faça, faça, só em X) sobrevivem no resumo; caminhos/versões/portas/IDs inventados; “veja acima” apontando para texto removido; se o resumo quase iguala os tokens que promete liberar; e podas sem contabilização. Uma medição em arXiv 2608.11242 encontrou ~17% de retenção das restrições entre compactadores. Inclui quatro ferramentas de agente, com varredura entre sessões que ordena conversas pelo dano da compactação. Determinístico, sem LLM: erro é defeito de regra identificável.