Plugins

Local-first persistent memory infrastructure for DeepSeek Harness: bounded hot-memory bootstrap, explainable cold recall (exact + Chinese BM25), lease-lock transactional writes, read-only governance, and trajectory review. Pure Python + Markdown, zero ext

Feishu (Lark) UI for DeepSeek Harness — a panel-driven control console: every slash command is a button on the ⚙️ control-panel card, in-card approvals and questions, live streaming cards, and one-QR app setup.

Agent Client Protocol (ACP) server plugin for the DeepSeek Harness (dsh) — drive dsh agents from Zed and any ACP client

A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.

Sélectionnez directement des éléments du navigateur pendant le Vibe Coding et envoyez un retour visuel structuré à l'agent DeepSeek Harness.

Importez les sessions, l'historique de chat et les agents de pi / opencode / codex / claude-code dans DeepSeek Harness — bouton de synchronisation en un clic, commandes slash, invite de migration au démarrage de la session

Alternative plugin market for DSH: curated catalog plus live GitHub browsing, zh/en cross-language search, a fail-closed pre-install static security audit with an install-hook block, and per-plugin README viewing with garbled-encoding repair.

Learning Mode agent preset: a coding agent that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style; installable via dsh plugin add (dsh-learning-mode on npm).

Génération automatisée de tests unitaires : une commande /testgen et un outil generate_tests qui échafaudent, exécutent et corrigent les tests jusqu'à ce qu'ils passent (générateurs LLM + modèles hors ligne ; vitest/jest/mocha/node:test).

Multi-provider account balance display for the DeepSeek Harness Web GUI. Queries real billing APIs (DeepSeek, StepFun, Kimi Coding, OpenRouter, MiniMax, xAI) and shows balance/quota in front of the model selector. Providers without an API-level billing en

Turns coding into an RPG: finished turns, tool calls and completed todos earn XP, with 27+ achievement badges, levels, titles and seasons. Event-driven scoring with a pure-function engine — the work itself is the game.

Bottom-right quota capsule that auto-discovers every configured provider (DeepSeek, OpenRouter, SiliconFlow, GLM, one-api/new-api, coding plans) and shows balance or rolling 5-hour and weekly usage, with per-provider visibility, alert thresholds and proxy support.

Superpowers (obra/superpowers) pour DeepSeek Harness : les skills de méthodologie de développement logiciel ainsi que leur amorçage de session, sous forme de plugin dsh.

Carte flottante déplaçable affichant le solde/quota de vos fournisseurs récemment utilisés (DeepSeek/Moonshot/Kimi For Coding) : découverte automatique, niveaux à code couleur, actualisation en direct.

Encodage base64/url/hex, hachages courants et génération d'UUID.

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

Sidebar file tree for DeepSeek Harness: a files panel with a lazy, per-extension-icon tree, copy-path and send-to-agent actions

Windows-adapted DeepSeek Harness coding-mode agent preset with a persistent PowerShell 7 shell.

Achievement and gamification plugin: unlock badges for turns, tool calls, sessions, daily streaks and coding behavior (edits/reads/tests), with a badge wall, unlock toasts and a ctx.achievements SDK.

Discord-native remote controller for DeepSeek Harness: drive persisted coding-agent sessions from DMs, mention-gated guild channels, and threads, with slash commands, progress updates, approvals, structured questions, and image and text attachments.

PR evaluation and improvement consultant: assesses PR success probability based on historical anti-patterns and success patterns, with one-click scoring and actionable suggestions.

Surveys local code and GitHub/npm for reusable implementations before development, evaluates reuse versus rewrite, and checks architecture coupling.

Runs scheduled coding tasks in isolated DeepSeek Harness sessions, managed from Settings or the agent.

Local toolbox for the DSH web GUI: 35 pure-client tools (text, encoding, hashing, extraction, conversion, reference tables) in a sidebar view, plus the /toolbox command and config-driven agent tool exposure.