DSH插件商店

cc-safety-net

kenryu42

A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

deja-vu

vshulcz

Memory for Claude Code, Codex, Cursor and 35 more coding agents, built from the session history already on your disk. Local search, MCP and hooks, no LLM, one Go binary.

engramory

tinqiao-oss

A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.

sofagent

KongFangXun

sofagent is an open-source FDE Harness for AI coding agents — on entry, write your business judgment into files (workflows, ontology, AI nodes); after departure, audit every change against them. 25 codified audit rules, tamper-evident chain, snapshots, and an MCP toolset (104 tools, 11 plugins). Everything can be FDEing.

everything-kiro

iamaanahmad

The complete collection of Kiro IDE configs, agents, skills, hooks, and MCP integrations for maximum productivity.

cc-notify-hooks

MarioZZJ

Agent 等待响应通知插件（支持Claude Code、CodeX、DeepSeek Harness、Reasonix） — 11 个渠道，短通知即时触达，长通知异步兜底。人可以闲着，Agent 不可以。

dsh-sentinel

fuhefei

Condition-driven wakeup for DeepSeek Harness: durable file/command/http/process/webhook watches that wake the agent, with dock, sidebar branch, and a global dashboard.

stent

omdsh-dev

灵感来源于MC Fabric的Cordis/DSH hook处理器

dsh-agent-plugins-market

Sivan757

One-stop skills, subagent, MCP and LSP manager for DeepSeek Harness (DSH) — compatible with Claude Code, Codex, Cursor, Kimi and other agent plugin layouts.

dsh-claude

Norman-else

Run Claude Code as a first-class DSH conversation while preserving its native agent loop, tools, skills, hooks, and MCP integrations in DSH.

chicheng-push

534119219

DSH(DeepSeek Harness) Web 消息推送插件：多渠道推送(Server酱/PushPlus/Bark/钉钉/企微/Telegram/飞书/Webhook等)，设置界面提供「推送插件」入口，可被其他插件调用(pushNotifier 服务 / /push/api 接口)

dsh-plugin-notify

c-ling

DeepSeek Harness 消息提醒插件：回合结束或等待确认时向浏览器、系统、飞书/钉钉/企业微信/通用 Webhook 发送通知

dsh-hooks

PeterBon

Config-driven lifecycle hooks plugin for DeepSeek Harness

dsh-notify-center

SingleOne

Native desktop and webhook notifications for DeepSeek Harness.

dsh-cc-ecosystem

Bcy2020

让 DeepSeek Harness 用上 Claude Code 全家桶:技能、命令、规则、权限、子代理、hooks—— .claude/ 资产原样加载

dsh-plugins

CREAIT-nl

Plugins for DeepSeek Harness: deep research as an agent preset, per-model generation limits, Claude Code hook compatibility, and web fetch/search tools.

Caushell

fatmo666

Compiler-style pre-execution safety analysis for Harness shell actions.

behavior-enhancer-generic

Zoria-Lind

Behavior discipline for coding agents: read-before-write enforcement, failure convergence, write verification with auto-rollback, and a high-risk command gate. Ships FULL plugin/hook adapters for DSH, Claude Code, Codex, and Pi, plus a host-agnostic SOFT skill with ADAPTIVE adapter guidance.

dsh-message-gateway

a792883583

Universal message-platform gateway for the DSH web GUI: WeCom AI bot / Telegram / Discord / QQ / Email bridges with per-chat sessions, streaming replies, and auto context compression

dsh-agentmemory

elementor-i

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

screenshot-feedback-hook-mcp

lkh081231

Let your coding agent SEE what it builds. Cross-platform screenshot feedback for AI agents: an MCP server, a Claude Code hook, and a native DeepSeek Harness plugin that drops screenshots straight into the conversation as images. Python + uv, zero install via uvx. Windows / Linux / macOS.

stalegreen

pavangupta352

Keeps a coding agent's green claims honest: verification runs are recorded unmasked, and done is blocked when the evidence is stale, failed or masked.

dsh-plugin-vet

wulun811

Trust pipeline for deepseek-harness plugins: deterministic static scan (11 rules) + LLM-driven audit protocol + two-part scorecard, with optional runtime guard (T1 sentinel / T2 fs & child_process hooks) and honeypot decoys. Monitor-and-alert only — vet never blocks or kills on its own.

dsh-feishu-bridge

wz-heng

Fail-closed Feishu (Lark) channel bridge for DeepSeek Harness (dsh) — chat with a bot, get agent turns back. Opt-in human-in-the-loop bash approval (Allow/Deny cards, fail-closed timeout), one-message /pair onboarding, webhook signature/timestamp/replay verification, daily latest-SDK canary. Community plugin, not DeepSeek-official.