Plugins

A visual plugin marketplace for DSH: browse multiple Git sources, install plugins with one click, and wire skills, subagents, MCP connectors, LSP servers and hooks into the harness automatically.

Matches prompts to installed skills for automatic activation, applies skill-declared lifecycle hooks and tool policies, and manages GitHub-hosted skills from Settings or the skill_manager tool.

Loads Claude-style plugins into DeepSeek Harness (dsh): discovers skills, commands and optional SessionStart hooks from Claude plugin directories, with hot command reload and uninstall cleanup.

Verifica as mensagens de commit do git conforme a convenção 7DGroup (etiquetas de tipo em chinês, regras de comprimento e pontuação) antes do commit, como uma proteção no lado do cliente antes dos hooks pre-receive do GitLab.

Ponte de compatibilidade somente leitura com o Claude Code para o DeepSeek Harness: Skills, Rules, Hooks de comando e Agents do .claude como SSOT.

Notificações de conclusão de tarefa via ServerChan / DingTalk / Feishu / webhooks genéricos.

Tarefas agendadas por cron ou pontuais: execute comandos de shell ou dispare webhooks conforme um horário, com entrega opcional dos resultados via ServerChan/DingTalk/Feishu/webhook.

DeepSeek Harness (dsh) host adapter for anysearch: thin Cordis bundle — hooks layer only, all business logic stays in the anysearch server over 127.0.0.1 HTTP IPC

Routes eight DSH lifecycle events through dedup, quiet hours and digest batching into seven channels. Severity maps to the fields Bark, ntfy, Telegram and webhooks actually support; failed deliveries retry with jittered backoff and survive a restart; per-channel circuit breakers stop hammering a dead endpoint; and a self-check reports a degraded relay instead of going silent.

Memory bridge between DeepSeek Harness and ai-memory: runs ai-memory's finalize-session when a DSH session ends, so the observations it already captured become searchable wiki pages. Skips subagents, queues concurrent session ends, and sweeps sessions abandoned by a forced restart. Requires a separately installed ai-memory server with its DSH lifecycle hooks wired by hand — ai-memory’s own install-hooks does not support DSH; this plugin only finalizes what capture has already recorded.

DSH plugin: audio chimes, cross-session toasts, desktop push, and IM webhooks for turn completion, errors, and approvals.

Pre-execution safety valve for DSH that judges with TypeSafe Jev: it hooks tools/pre-execute and decides every bash/pwsh call by first applying offline static rules, then by asking the Jev model — the System One model from TypeSafe, which returns a structured decision instead of prose — one yes-no question ("will this command irreversibly delete or overwrite real data?"), turning the answer into allow, revise, block or escalate; revise hands the model a safer rewrite, escalate offers a one-shot human token; exhausted credit or a missing API key degrades loudly instead of failing silent, and a missing key is requested in the conversation itself (`guard key set`, read from stdin); every verdict is appended to a shared audit log and the text people read is bilingual zh-CN/en.

DSH 宿主上的 SBTD workflow 适配器。当前为 T5：注册短中文 sbtd section、进程内会话状态、`sbtd_plan`、`sbtd_review`、`tools/pre-execute` / `agent/pre-step` hooks 门禁，以及从 640-skills 只读同步的 `manuals/`。

Keeps DSH agents from forgetting your requirements during long tasks. It saves important conditions and completion evidence locally, brings them back after context compaction or session resume, and stops partial work from being reported as the whole task done.

A DeepSeek Harness plugin that records which files the agent edited, with which model, and in which session into git-ai

One-click Claude Code and Codex hooks for DeepSeek Harness: auto-discovers your existing hooks config and runs it on the official bridge plugins.

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.