Plugins

Un coffre Obsidian partagé pour tous les agents : cœur Python sans dépendances (recherche/promotion/arbitrage/oubli), modèle de coffre, plugin dsh (memory_search/show/submit/status).

File d'attente de tâches inter-sessions avec notes de passation : les sessions et sous-agents publient, réclament, terminent et annulent des tâches sur une file partagée sauvegardée sur fichier, et laissent un résumé de passation pour la personne suivante.

Compares coding agents in isolated Git worktrees with deterministic validation, scoring, and explicit winner application.

team-task for DeepSeek Harness: long-horizon multi-agent tasks — a lead plans a reviewed DAG, durable members execute, an event log is the single truth, and a resident reconciler survives crashes and restarts.

GPT plans dependency DAGs, DeepSeek workers execute tasks with adaptive parallelism, and an optional GPT reviewer audits incremental Git diffs and drives repair rounds.

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

Préréglage + pack de skills RigorQuant : recherche multi-agents sans surveillance et cloisonnée pour les mathématiques empiriques et computationnelles (économie, finance, portefeuille), avec une batterie de vérifications en quatre parties avant implémentation et une voie d'escalade jacobienne/Lean.

Relais de contexte asynchrone, résumé par LLM, entre les sessions DSH et les Agent Team Rooms autorisées, avec instantanés instantanés et résumés planifiés.

Run Claude Code and Codex as live terminal panes beside dsh: a split view in the web UI, buttons to seat them, and tools that let the dsh agent hand them work and read their screens.

A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.

TaskSwarm (essaim de tâches) — plugin d'orchestration de tâches multi-agents pour DeepSeek Harness : exécution parallèle en vagues/voies, isolation par git worktree, paquets de tâches et revue inter-modèles, récupération après plantage.

Découverte et communication inter-sessions sur le même runtime pour DeepSeek Harness.

AgentMonitor multi-agent monitoring panel for the DeepSeek Harness — a sidebar entry that serves an embedded agent-monitor dashboard via the /agentmonitor webserver route. Ships a self-contained static dashboard (works out of the box) and lets you point d

DeepSeek Harness bundle that registers Claw Orchestrator as an ACP subagent provider — delegate a dsh subagent to a multi-engine council across Claude Code, Codex and Cursor.

OpenClaw Enterprise AI Team bridge for DeepSeek Harness

DeepSeek Harness (dsh) plugin: run work as a small crew of role agents (product manager, engineer, code reviewer) that talk through files on disk, with the PM as the only voice to the user.

Adversarial code review — parallel finders inspect a diff through separate lenses (correctness, lifecycle, contract, security), then each finding goes to independent verifiers tasked with refuting it, and one refutation drops it.

Multi-agent deep long-form article pipeline skill for DeepSeek Harness, running 7 roles across 5 phases with parallel literature/data/case retrieval, an evidence base, independent audit and human verification gates.

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.