Plugins

Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.

Integración profunda con Mnemon: memoria local de tres niveles (Runtime Memory, Documents recuperables y Memory Spaces supervisados).

把Claude Code的UltraCode模式带给DSH，把 DSH 的一次性多 Agent 调度，升级为可生成、可保存、可治理、可观察、可恢复的 Workflow 层

Orquestación multiagente al estilo UltraCode: una capa de flujos de trabajo generable, guardable, gobernable, observable y reanudable.

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

Persistent multi-model squads configured in Settings and selected in the Composer, with per-member model/tool policies; the main Agent dynamically plans each send as a bounded DAG with bounded reviewer/repair loops, while Run Center tracks retries and per-member tokens from official Harness usage events.

Herramientas Cordis de DeepSeek Harness para All in Flash, impulsadas por All in Luna

Model high-availability failover (quarantine, circuit breaking, probe recovery) and subagent orchestration (fanout/pipeline/supervisor) with bilingual settings UI.

Salas persistentes para sesiones independientes de agentes de DSH, con membresía explícita, mensajes directos y de difusión, seguimiento de tareas y una línea de tiempo web compartida.

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

Relevo de contexto asíncrono y resumido por LLM entre sesiones de DSH y Agent Team Rooms autorizadas, con instantáneas inmediatas y resúmenes programados.

Plugin de proveedor opcional para dsh-skill-pack-security: registra la edición skills/ (zh) o skills-en/ (en) del pack en ctx.skills. Incluye ambas ediciones integradas en pack/.

Un plugin de meta-agente nativo del modelo para DeepSeek Harness: el modelo sintetiza en tiempo de ejecución flujos de trabajo específicos para cada tarea a partir de cinco patrones de flujo agentivo (encadenamiento de prompts, workers paralelos, router, supervisor, bucle de evaluación) y coordina herramientas y subagent

Long-task orchestration loop: Codex plans/scores/reviews, DeepSeek executes, Kimi supplements (vision acceptance, summarization, cross-check).

Enrutador de modelos de dos niveles para DeepSeek Harness: enrutamiento con LLM-Judge, cadenas de respaldo multimodelo, conmutación por error con retroceso exponencial y orquestación a nivel de tarea (adaptación a DSH de pi-shift-router)

Alternative WorkflowEngine provider for DSH 0.1.0-rc.7 that runs model-written orchestration in fresh QuickJS/WASM runtimes with a JSON-only host bridge and bounded memory, execution time, and child-agent fan-out.

A single project operating map for DeepSeek Harness.

Main-brain orchestration preset: delegation-first persona, root-session execution gate, and portable AI-LAW rule skill.

Declarative task-DAG orchestration for DSH: validates dependency graphs, runs topological task layers in parallel through workflow-backed subagents, and propagates failures deterministically.

Rigorous open mathematics research suite: four agent skills (rigorous-open-math-research, manage-math-research-program, math-research-workflow, lean-verify) for theorem solving with adversarial audit, research program management, pipeline orchestration, and Lean 4 formalization audit; CI-verified tests and mechanical upstream sync.

Discover and verify portable RoleHub roles, pin each exact bundle, then launch its prompt and bundled skills in an isolated, continuable DSH Session with Host-approved tool bindings and optional Agent Team Room attachment.

Plataforma de evaluación de agentes: benchmarks en YAML, orquestación de ejecuciones headless, métricas basadas en trazas e informes de ejecución