Plugins

Static and runtime security guard for dsh: rule-based scans for malicious code, prompt injection and token waste, runtime interception of dangerous tool calls, /scan command, plugin_scan tool, web panel, and allowlist.

One-command bundle of the three AgentFrame plugins: memory-director, compaction, and aura-scheduler together.

Manage and organize your agent skills by category, tags and collections in DeepSeek Harness, with a settings panel and a slash-command folder picker.

Update checker (npm edition): a settings page comparing local and latest versions of @deepseek-ai/dsh and every installed plugin, with a red-dot nav reminder and ready-made update commands.

Bidirectional Feishu/Lark channel for DeepSeek Harness: persistent conversations, true streaming replies, 40 MCP Feishu tools, slash commands, and an IM-bot status tab in the plugin settings.

Cron/one-shot scheduled tasks: run shell commands or fire webhooks on a schedule, with optional ServerChan/DingTalk/Feishu/webhook delivery of results.

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics, and verifiers.

HTTP/API debugging toolset: full-control HTTP requests (method/headers/body/auth), curl command parsing and one-step execution, in-session request history with side-by-side response comparison, pagination-aware Link headers, and DeepSeek-branded UI cards (optional dsh-http-tools-ui).

Relecteur de diff incrémental pour DSH : après approbation d'un lot, seuls les changements depuis le checkpoint sont affichés, avec un panneau de revue Web et la commande `/review` qui réinjecte le feedback à l'agent.

Frontend Pi TUI (framework de terminal à rendu différentiel) : markdown en streaming, repli de la réflexion, cartes d'outils, commandes slash, superpositions d'approbation/question, magasin de session dsh partagé.

Plugin fournisseur Command Code pour DeepSeek Harness (dsh) — fonctionne avec tous les plans Command Code, y compris le plan Go à 1 $ ; utilise la clé API d'authentification Studio via /alpha/generate, pas la Provider API.

Hub de skills global pour dsh : agrège les skills Claude Code, de projet et .skill-package dans ~/.dsh/skills, avec import par référence ou copie et usage via le menu slash.

Bundle ACP DeepSeek Harness pour la délégation à l'éditeur : un profil de serveur stdio Agent Client Protocol en une commande, qui partage les identifiants et journaux de session dsh.

La CLI compagnon manquante pour DeepSeek Harness (dsh) : gérez les serveurs MCP en une commande — ajout/liste/suppression/test avec vérifications de connexion à blanc, plus un import en un coup depuis Claude Code / Codex. Se monte aussi comme plugin dsh pour que l'agent puisse gérer MCP lui-même.

Un palier de permission intermédiaire pour DeepSeek Harness entre workspace-write et danger-full-access : approuve automatiquement les commandes et opérations inoffensives ciblant des zones de confiance configurées, au-delà de l'espace de travail courant.

/repro exporte un lot de problème minimal, nettoyé des secrets et rejouable : le journal de session, les commandes échouées et le diff Git.

Un tableau de commandes flottant qui liste toutes les commandes slash de DeepSeek Harness sous forme de boutons exécutables, triés par usage.

AlphaRSI — three-role self-improvement loop that evolves the training recipe of alpha sequence models. Operator runs walk-forward, Evaluator grades with OOS RankIC, Refiner proposes hyperparameters via TPE Bayesian search; only strictly-better recipes are kept. Offline one-command run, data bundle shipped with sha1 reconciliation, GPU auto-detect. Ships one skill.

End-of-chat visual storyboard: a storyboard tool renders a self-contained HTML card (inline SVG diagram, numbered flow, facts grid, timeline) from a JSON spec, writes it under ~/.dsh/storyboard/<session>/ and opens it in the sidebar; a system-prompt section and a /storyboard command trigger generation. Server-only, zero runtime dependencies.

Dynamically trusts every Host header that actually arrives and flips the default web binding to 0.0.0.0: wildcard or unenumerable entry domains work without editing the start command, the authentication layer is untouched, and hosts are evicted by LRU beyond a capacity cap.

Query and manage JumpServer through conversation: assets, users, accounts, permissions, sessions, command audit logs, command filters, and RBAC roles, authenticated with an AccessKeyID/AccessKeySecret pair (HTTP Signature).

Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (pwsh, bash, write, edit) advertise the full sandbox_permissions enum, but DSH only accepts a level strictly wider than the one already in effect — a check its own source calls 'deliberately not a schema constraint'. A model that reflexively passes the argument therefore picks the level it is already at and the call dies before running with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "workspace-write" mode', costing some models a whole turn of retries. This plugin registers one tools/execute waterfall listener and, only on that documented rejection and only when the arguments really carried an escalation field, re-issues the identical call once without it. Safe by DSH's own documentation: the rejection precedes any execution ('nothing has run'), and the corrected call cannot match again, so the retry is loop-free. Reproduced and verified end to end — before: isError true, the command never ran; after: the command's real output, isError false, one tool/call and one tool/result. Zero dependencies.

Deterministic engineering orchestration runtime for DeepSeek Harness: the orbit_controller tool and OrbitService run Commander, Executor and Smart Watchdog children through PLAN, EXECUTE, EVALUATE, bounded correction and runtime recovery, with durable state in <project>/.cx/state.json.

Exa-backed web search provider for the ctx.web seam, with Exa Dynamic Highlights on by default and the Exa-Beta header that setting requires; exposes all eight Exa retrieval types, adds an /exa command to change highlights, search type and result count at runtime, and registers an exa_search tool that takes its own result count.