Plugins

Migre et importe une configuration complète de Claude Code ou Codex vers DSH. Compétences, commandes slash, serveurs MCP, hooks, sous-agents et règles de permissions, avec une estimation de migration en mode simulation (dry-run), un rapport de différences de migration et un contrôle post-migration ; s'installe comme extension exposant un outil movein_from_claude_code afin que l'agent puisse effectuer la migration pour vous.

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/ plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via a memory-IR parse layer that keeps .claude as the source of truth with no writes back. Six installable packages: loader, skills, permissions, agents, hooks, mcp.

agentmemory for DeepSeek Harness (dsh): full memory_* tools, capture hooks, and context injection over the local REST server

A starter template for dsh plugins covering config, tools, events, services, hooks, browser UI slots, and slash commands.

Multi-channel push for DeepSeek Harness: Server酱, PushPlus, Bark, DingTalk, WeCom, Telegram, Feishu, ntfy, custom webhooks and more, configurable from the settings panel and callable by other plugins via the pushNotifier service.

SHOPLINE AI Toolkit : relie le serveur MCP officiel SHOPLINE Developer et fournit sept skills d'agent SHOPLINE (Admin REST, GraphQL, OAuth, webhooks, Sline) — l'équivalent SHOPLINE du Shopify AI Toolkit.

Task-completion notifications via ServerChan / DingTalk / Feishu / generic webhooks.

Config-driven lifecycle hooks: event→command declarations in cordis.patch.yml, with Feishu card notifications and a QR scan-to-create bot setup.

Install suites from any Claude Code, Codex, Cursor, Kimi or agent-plugins.org git marketplace repo — skills, MCP servers, hooks and slash commands are injected into DSH sessions at runtime, with a market page in the Web GUI.

Checks git commit messages against the 7DGroup convention (Chinese type tags, length and punctuation rules) before committing, as a client-side guard before GitLab pre-receive hooks.

Read-only Claude Code compatibility bridge for DeepSeek Harness: Skills, Rules, command Hooks, and Agents from .claude as SSOT.

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

Honesty guardrails on the tool pipeline: blocks a coding agent from weakening tests, swallowing errors, stubbing type checks, or deleting tests through the shell — nine deterministic hooks, each backed by a planted-failure test proving the guard can fail.

Reuses hooks declared in Claude Code, Codex and opencode configs on dsh, executing shell, webhook, oracle and proxy handlers with zero runtime dependencies.

Hooks de cycle de vie façon Claude Code : des commandes shell configurées s'exécutent avant/après les appels d'outils du modèle avec une charge JSON sur stdin ; un code de sortie non nul avant l'outil bloque l'appel.