Plugins

Gerenciamento de sessões arquivadas, notificações de parada de tarefa, um verificador de atualizações, roteamento de modelos (regras por palavra-chave + model_route com allowlist), gatilhos agendados multi-tarefa (heartbeats e tarefas em horário fixo) e uma navegação de rolagem de mensagens no estilo DeepSeek para a UI web do dsh.

Ferramentas Grafana só de leitura que consultam métricas através do proxy de fontes de dados: estado da instância, listagem de fontes de dados, consultas PromQL instantâneas e por intervalo, estado atual dos alertas e regras de alerta aprovisionadas. As consultas por intervalo são reduzidas a um orçamento de pontos; um step fornecido explicitamente que o excedesse é rejeitado em vez de alterado em silêncio, para que o modelo nunca receba dados com uma resolução que não pediu.

Secção de Settings para sessões arquivadas: navegue por espaço de trabalho, pesquise, desarquive em lote com atualização em direto da barra lateral e use regras opcionais de arquivo automático (dias inativo, manter os últimos N por espaço de trabalho) com pré-visualização de execução simulada — além de uma barra de turnos na borda esquerda para saltar entre turnos de conversas longas e histórico de entrada ↑/↓ no compositor.

Plugin de domínio de desenvolvimento Rust para DeepSeek Harness (dsh): pirâmide de verificação fmt→clippy→build+test→miri+audit(+semver) como ferramentas voltadas ao modelo + governança em camada de grafo (8 regras anti-Goodhart, incl. densidade de #[allow] / testes excluídos, blind-spot via Cargo.toml e pub

Motor de regras de permissão no estilo Claude Code: níveis hard/deny/ask/allow com um nível hard acima do acesso total, regras por workspace, proteção de caminhos com curinga e um editor visual por etapas; as regras persistem em settings.yaml.

Prompts de regras ao estilo rules.md do Claude Code: ativa ficheiros Markdown de regras através de correspondência glob com os ficheiros que um agente lê ou edita, com suporte para injeção e ordenação de prompts.

Gerenciador de regras, comandos e habilidades para o dsh: comando /rules, painel de configurações com edição visual de regras (adicionar/editar/desativar/excluir, suporte a zonas livres), comandos personalizados do usuário com argumentos {input}, gerenciamento de habilidades e backup automático com restauração de um clique do AGENTS.md.

Organiza a navegação de configurações do DSH: agrupa entradas de plugins de terceiros sob linhas de grupo recolhíveis, com grupos personalizados no estilo de favoritos, um botão de recolhimento e classificação automática (tags do mercado → regras de nome → seu modelo de IA).

Settings-UI editor that assigns per-teammate model and reasoning-effort rules for DSH native agent teams, resolved at spawn time by wrapping SubagentRuntime.startContinuable. No official files are modified.

DSH plugin that registers the ai-eight-honors-eight-shames skill: eight checkable working rules for coding agents (verify before calling, confirm ambiguity, cite evidence, reuse before creating, test before claiming done, follow local conventions, separate fact from inference, keep changes reversible) plus a ninth rule that logs each user request and the change made in report files at the workspace root.

Audio cues for DeepSeek Harness: a short synthesized sound when an agent needs confirmation, finishes a turn or a background job, or fails, with five sound packs, per-event toggles and volume, and do-not-disturb rules stored in the host settings document.

DSH plugin that registers the ai-eight-honors-eight-shames skill: eight checkable working rules for coding agents (verify before calling, confirm ambiguity, cite evidence, reuse before creating, test before claiming done, follow local conventions, separate fact from inference, keep changes reversible) plus a ninth rule that logs each user request and the change made in two fixed report files at the workspace root.

Ponytail lazy-senior-dev ruleset for DeepSeek Harness: a 7-rung minimal-code ladder (YAGNI, reuse, stdlib, native, installed deps, one line, minimum), six skills (main rules, over-engineering review, repo audit, debt ledger, gain scoreboard, help), a /ponytail session command for lite/full/ultra/off levels, and optional always-on ruleset injection via config. Vendored verbatim from upstream ponytail (MIT), zero tools registered, clean uninstall.

Skill that fact-checks a claim against the open web rather than model memory: it splits the claim into independently checkable fact points, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster and accidents, food safety, science, education, sports, entertainment, judicial, and more), searches domestic and international ecosystems in parallel, fetches primary pages, grades sources by type, re-searches with debunking keywords, and reports conclusion-first with a full URL and citation position behind every statement, keeping unverified and undecidable points separate from confirmed ones. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

Blocks an agent from reading, searching, writing, or editing chosen files and directories, keeping their contents out of the conversation — including sensitive-word files whose text can make later provider requests fail with a 400. Rules are picked from a file/directory browser on the plugin page.

Filesystem permissions for shell calls, granted per path and capability rather than per command name. The command line is parsed for the read, write, create, delete and execute effects it needs, a capability it lacks raises the approval card instead of a flat refusal, and the same rules are compiled into the macOS Seatbelt profile the process, its children and the code its arguments never showed all run under. An Approvals tab in the conversation reads the audit log back and shows which rule, automatic reviewer or person answered each call.

BaziDIY ontology plugin: deterministic bazi/wuxing/bead/style rules as DSH tools (calculate_bazi, propose_designs, generate_design, save_design, load_design), plus bracelet SVG rendering and a bead editor; no LLM calls inside execute.

Mobile-first Web UI quality-of-life pack for the DeepSeek Harness: a Chrome-style active-session tab bar, full-screen sidebar swipe open/close, overlay sidebar, collapsed-sidebar recents, keyboard-suppressing session switching, viewport/IME keyboard adaptation, touch feedback, code/table inner scrolling, hidden permission dropdown, a full-screen settings rewrite with tab memory, and a compositor-driven status pulse, no-touch-drag long-press protection — 14 features, each independently toggleable from the Settings QoL section with instant effect, persisted per browser in localStorage; pure client-side CSS/JS, mobile rules locked to viewports of 768px and below so desktop stays untouched.

Reads .mcp.json from the .dsh home and from the agent workspace, mounts every mcpServers entry into DSH, and adds an MCP tab in the Web UI for listing, adding and unloading servers.

Injects the rule files under $DSH_HOME/rules and <cwd>/.dsh/rules into the conversation at the first agent pre-step, re-injecting them after compaction.

Language-pack framework that rewrites model replies: A is an independent LLM rewrite, B injects FTS5 terminology retrieval into that rewrite, C applies local dictionary and regex rules, and composite runs a pipeline such as B then A then C. Ships a GitHub pack marketplace, a ZIP installer with path, size and file-type checks, and a mandatory risk disclaimer gate.

Hot-switches in-process DSH fetch traffic among direct, manual HTTP(S)/SOCKS5 proxy, and ambient system-proxy modes, with no-proxy rules and optional proxy-environment export for newly spawned child processes.

Team cost captain: meters every model call (subagents included), attributes each call to a member by workspace rules, prices it with the built-in DeepSeek 2026-09 catalog (peak/off-peak, CNY/USD) or user overrides, and appends it to a local JSONL ledger. Adds hot-reloadable member budgets, 80%/100% webhook alerts, optional over-budget enforcement, a team_cost_report tool with CSV export, and a settings-page team dashboard served over a Typert RPC service.

Task board plugin for the DSH web GUI: a sidebar entry plus a multi-column kanban view with real execution through DSH sessions, schedules, session rules and auto-cruise automation. Board truth lives on the host and syncs to every device over SSE (the bro