Plugins

Pesquisas ramificadas na Web GUI: ferramenta ask_survey com roteamento por opção, insights ao passar o mouse, diagramas Mermaid, modelos de resposta com um clique e progresso salvo que pode ser retomado.

Gestão de progresso de laboratório/projeto para DeepSeek Harness: 16 ferramentas agent progress_* (CRUD de itens, páginas de quadro diário, registros diários, busca global, visão geral, Gantt, comentários, importação/exportação) e aba “进度” no better-sidebar com a Web UI original. Os dados ficam em `.progress/progress.json` do projeto da sessão.

Envia automaticamente o progresso das conversas ao Tencent IMA (nota diária e base de conhecimento Work), espelhando o fluxo local Claude Code ima-upload.

Plugin DSH independente com 21 ferramentas de governança do ciclo de vida, todas somente leitura: classificação de tarefas; validação de estado, plano e evidências; pré-verificação e agregação de gates; auditorias de lançamento e instalação; análise de contexto e progresso; caminho crítico; reconciliação ao retomar; e prévia de mudanças que sempre nega a execução. Instale pelo npm como `@240xu/dsh-tech-lead`.

Pesquisas ramificadas na DSH Web GUI: `ask_survey` oferece roteamento por opção, informações ao passar o cursor, diagramas Mermaid, modelos de resposta com um clique e retomada do progresso salvo.

Habilidade de dashboard multi-agente para o DeepSeek Harness — relatórios de status, rastreamento de tarefas, visualização de progresso.

Companheiro baleia arrastável com progressão local, conquistas, skins e rastreamento de atividade que preserva a privacidade.

Contabilidade pessoal para o DeepSeek Harness: registre despesas e receitas (unitárias ou em lote), liste, estatísticas mensais e anuais com tendências, orçamentos com progresso e alertas de estouro, restauração após exclusão lógica e relatórios CSV e HTML autocontidos. Sem dependências, JSON local.

Ferramentas de arquivo S3, FDS e FTP para DeepSeek Harness: 8 ferramentas de agente (list, stat, mkdir, delete, move, copy, download, upload) — mutações com aprovação, jobs de transferência com progresso e cancelamento.

Rick and Morty para a interface web do dsh: skin de três visuais (verde portal C-137 / jaleco / azul Meeseeks) mais um companheiro pet de desktop com seis personagens, falas bilíngues, humores dirigidos pelo agente, carinho combo e painel de progressão

Painel em tempo real de etapa, ETA e custo para tarefas dsh headless: transforma o fluxo de eventos de sessão opaco em uma grade multitarefa viva (plugin cordis + painel local independente, sem chamadas de API).

Descoberta de ferramentas sob demanda por agente e divulgação progressiva de esquemas

A five-stage engineering loop for agent-built projects — spec, build, verify, ship, learn — with one artifact and one gate per phase, so an agent always knows the single next action. Role policy, project templates and deployment sit behind explicit ports: swap the implementation without rewriting the loop. Its scaffold generator lays out the internal layers of a project — `init --layout {none,webapp,service,plugin} --stack {python,node,none}` — from nine layers sampled out of three unrelated production projects: entry docs, an OpenSpec plan face, a spec truth layer (INDEX, one file per domain, TESTING, CONSTITUTION), a wiki split into knowledge / progress / runbook, the six `.agents/` slots, server+web, scripts/deploy/config, tests+e2e and a gitignored out/. Non-none layouts also gate the directory contract and compile every source root. Ships a Python CLI (init/next/check/ship/new) plus a local command adapter and an SSH/systemd adapter with release directories, an atomic current/previous switch, a deploy lock, a commit-versioned JSON probe and automatic rollback on a failed probe; bootstrap and teardown provision and remove the unit and the reverse-proxy block idempotently and refuse to delete a root they did not create. Includes a runnable example workspace and a skill that keeps the agent on one phase at a time. Requires Python 3.10+ and PyYAML; remote deploys need SSH access, rsync, systemd and Caddy on the target.

Runs Hindsight long-term memory on your own machine: after a one-time uvx --from hindsight-embed@latest hindsight-embed profile create server setup (~450 MB of Python dependencies) and with your own LLM key, the plugin manages the local memory server itself (health probe, start, stop, logs), registers ten hindsight_local_* tools for status, page search, page read, recall, remember and reflect, injects a knowledge-page index once per session, writes each finished turn back into the bank, and extracts facts with your own LLM key. Do not enable it alongside the official @vectorize-io/hindsight-coding-agents plugin: both read the same bank and would inject duplicate context. At session end it writes a handoff snapshot that the next session injects as previous progress. The data directory is configurable (dataDir) and scripts/relocate.mjs moves an existing install to another drive, creating directory junctions where the server hard-codes its paths.

PTC agent preset whose tools.guard refuses tool calls until the session holds an active goal and an in-progress todo.

Makes the agent narrate progress during long tool chains instead of staying silent until the final answer: a standing system-prompt rule that travels with every request, plus a notice injected after every N tool calls. A panel on the plugin page tunes the cadence, the reminder budget, and both texts; changes apply live.

A countdown pill under the message composer showing how long is left before you clock off, with a workday progress bar; click it to set your own start and end times (saved in this browser), and after the end time it turns into an overtime timer.

Page-level startup splash: a Penrose triangle light sweep over a living isometric diamond ocean, where the frame itself is the progress gauge, paced by the intro but capped by real DSH boot milestones. Any bare key skips it, ten palettes come from Monument Valley and Geometric Islands, and when the intro ends the triangle stays on as a small mark beside the composer that reflects what the agent is doing.

An enhanced fork of PC2005-cloud/dsh-pet (do not install it alongside the upstream dsh-pet): a desktop pet for DSH with schedule reminders, approval and question bubbles you can answer in place, a 20-entry history ledger, double-click corner cycling, a configurable data directory, a step/elapsed progress line, snooze and one-hour mute, a right-click menu whose order and hidden items you can edit in settings (chat first by default), and a task-queue progress bar inside the work bubble.

Counts the assistant rounds that call tools without writing anything to the user, then inserts a short progress reminder as a visible user message at the next model-request boundary, so a long silent tool loop reports what it has done before continuing. A Settings page adjusts the silence threshold (default 10), the reminder wording, the language (en / zh-CN / zh-TW), whether the reminder repeats every further threshold of silent rounds, whether subagent sessions are counted, and whether Agent Teams nudges the lead only or every member.

A draggable square-cake mascot that runs while a turn is in progress, sleeps when it finishes, and gets angry on errors.

Bilibili music player for the DSH composer dock: import your Bilibili login cookie and a listening-profile JSON for profile-based recommendation with like/skip/dislike feedback and 192k playback; without a profile it falls back to genre-based online search and progressive playback.

Daily check-in for Nanjing Forestry University's ACM AI Hub plus seat booking for its library — both site addresses are hardcoded — with a settings page and a progress badge; built for DeepSeek Harness Mobile (DSHM) on Android.