Plugins

Command-triggered red/blue adversarial review for ANY plan (not quant-specific). /plan-adversarial <plan>: arms a gate that requires the agent to derive two independent subagents (red=attack, blue=defend), have them converge on a consensus plan with NO th

Modo de permissão intermediário entre workspace-write e acesso total: comandos de shell são verificados por regras determinísticas e por uma revisão de subagente; ações irreversíveis ou de nível de sistema exigem aprovação explícita.

Delegação hierárquica para subagentes: roteamento de modelos por função com failover, esforço de raciocínio por rota, rótulos que ocultam o modelo, delegação por fork e um editor visual de rotas.

Expõe métricas Prometheus delimitadas para sessões, agentes, chamadas de LLM, ferramentas, aprovações, subagentes e jobs do DSH, com um painel no Grafana e um endpoint apenas em loopback por padrão.

Prompt mínimo x capacidades PTC web: persona de uma linha, SDK run_code, subagentes, Ralph, busca/obtenção na web e Windows Git Bash; a ferramenta de fluxo geral permanece oculta.

Visão para qualquer rota do DSH: cole imagens no compositor web com análise automática guiada pela intenção, delegue a leitura de imagens do workspace a um subagente de visão Kimi/MiniMax e materialize os originais colados para edição.

Carregamento de plugins em tempo de execução para a Web UI: um diretório monitorado (hot directory) instala/atualiza pacotes de plugins de cliente ao vivo em toda página aberta, sem reiniciar. Inclui um exemplo de dashboard de subagentes na coluna direita

Cut LLM costs: route routine tasks to cheap subagent models (DeepSeek Harness plugin)

中瑞世联工作台 / CRWU audit workbench for DeepSeek Harness: pick a pending audit report, dispatch one AI audit subagent, watch and stop/restart it, auto-upload deliverables to Aliyun OSS.

dsh plugin: unattended approval gate — subagent/scheduled/cron approval requests get a bounded answer window, then settle with a fail-closed default instead of hanging forever (per origin or per session)

DeepSeek Harness plugin that asks which provider and model should run each delegation before the child starts, so a subagent can go to a cheap or local route instead of the parent's.

Active wait for background subagents in DeepSeek Harness: registers a wait_subagent model tool that blocks until a named background continuable subagent settles, then returns its stop reason and closing message — optional timeout, membership gate rejects unknown ids, event-driven with zero polling. Closes the gap between run_in_background fire-and-return and the async settlement notice; wait for a background subagent without polling list_agents.

Role-based subagent delegation for DeepSeek Harness: one delegate tool over a folder of role files, with a roster that ships and stays overridable

Memory bridge between DeepSeek Harness and ai-memory: runs ai-memory's finalize-session when a DSH session ends, so the observations it already captured become searchable wiki pages. Skips subagents, queues concurrent session ends, and sweeps sessions abandoned by a forced restart. Requires a separately installed ai-memory server with its DSH lifecycle hooks wired by hand — ai-memory’s own install-hooks does not support DSH; this plugin only finalizes what capture has already recorded.

OpenRouter provider that reads the live /models list, so new models appear without a harness release: models sorted by name with input/output prices, per-model reasoning levels, image input, reasoning_details replay, Anthropic prompt caching, and actual spend per session including subagents from OpenRouter usage.cost, shown under the Web UI composer and by /cost.

Session change-review for DeepSeek Harness: tracks write/edit tool calls and renders VS Code-style side-by-side diffs via diff2html, auto-following the theme, with subagent aggregation and one-click revert.

Long-term memory for DeepSeek Harness, read-only as of 0.1.0: a scribe_recall tool that reads a plain-markdown memory room, path rules that refuse directory traversal, Unicode smuggling and NTFS alternate data streams, and a bounded index whose truncation is always reported rather than silent.

A continuation of simon300000/dsh-auto: the Auto Approve permission preset for the DSH Web UI reviews each approval with one single-shot model call instead of a reviewer subagent, auto-approves only the actions that pass and hands the rest to human approval, and remembers confirmed decisions as project- and global-scope allow/deny lists, with an approval timeline in the right sidebar.

Automatically orchestrates complex DeepSeek Harness requests. It detects when delegation is useful, builds a dependency-aware plan, assigns bounded researcher, architect, backend, frontend, tester, and documentation workers, collects structured evidence, and sends the results to a final reviewer. The bundle atomically enables the workflow engine and model-facing subagent tools; disabling the plugin disables its complete tool group as well.

Ships a skill about handing work to subagents instead of doing it inline - which tasks are worth fanning out, how many to run at once, how to send them in parallel, and how to check what they returned instead of trusting the summary.

Live change review for DeepSeek Harness: tracks write/edit tool calls per session, lists changed files above the composer and opens each file's line-level diff in a plugin-registered right-sidebar tab, with session-log / initial-version / Git comparison modes, per-change and per-file revert, subagent aggregation and SSE updates. A fork of cirelir/dsh-change-review rebuilt around the right sidebar.

Flip the DSH page over to a glass task board showing live jobs, subagents and session state, with an infinite canvas that unrolls a card into draggable controls, embedded web-app frames, and a conversation box that edits the canvas.

In-process DeepSeek Harness subagent provider that seeds a child with only the last N completed parent turns (fork-lite), leaving official fork untouched.

Named, file-defined subagent roles for DeepSeek Harness: persona, subagent-only skills, tool permissions, an ordered model chain with failover, and derived groups.