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).

Inkrementeller Diff-Reviewer für DSH: nach Freigabe eines Batches werden nur neue Änderungen seit dem Checkpoint gezeigt, mit Web-Review-Panel und `/review`-Command, der Feedback zurück an den Agenten injiziert.

Frontend Pi TUI (Terminal-Framework mit differenziellem Rendering): Streaming-Markdown, einklappbares Denken, Tool-Karten, Slash-Befehle, Genehmigungs-/Rückfrage-Overlays, gemeinsamer dsh-Sitzungsspeicher.

Command-Code-Provider-Plugin für DeepSeek Harness (dsh) — funktioniert mit jedem Command-Code-Tarif, einschließlich des 1-Dollar-Go-Tarifs; nutzt den Studio-Authentifizierungs-API-Schlüssel über /alpha/generate, nicht die Provider-API

Globaler Skill-Hub für dsh: bündelt Claude-Code-, Projekt- und .skill-package-Skills in ~/.dsh/skills, mit Import per Referenz/Kopie und Nutzung über das Slash-Menü

DeepSeek-Harness-ACP-Bundle für die Delegation an Editoren: ein per Einzelbefehl startbares Agent-Client-Protocol-stdio-Server-Profil, das dsh-Zugangsdaten und Sitzungsprotokolle teilt.

Die fehlende Begleit-CLI für DeepSeek Harness (dsh): MCP-Server mit einem Befehl verwalten — add/list/remove/test mit Trockenlauf-Verbindungsprüfungen, plus einmaliger Import aus Claude Code / Codex. Lässt sich auch als dsh-Plugin einbinden, sodass der Agent MCP selbst verwalten kann.

Eine mittlere Berechtigungsstufe für DeepSeek Harness zwischen workspace-write und danger-full-access: genehmigt harmlose Befehle sowie Operationen auf konfigurierten vertrauenswürdigen Bereichen außerhalb des aktuellen Arbeitsbereichs automatisch.

/repro exportiert ein minimales, von Geheimnissen bereinigtes, reproduzierbares Problem-Bundle: Sitzungsprotokoll, fehlgeschlagene Befehle und Git-Diff.

Ein schwebendes Befehls-Deck, das jeden Slash-Befehl in DeepSeek Harness als ausführbare Schaltfläche auflistet, sortiert nach Nutzungshäufigkeit.

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.