CATEGORY
Verified manifests and exact versions in this category.
@zseven-w/dsh-crew
DeepSeek Harness plugin: dispatch work to DSH agents from Claude Code / Codex, as native subagents with live progress
@aa2246740/dsh-skillhub
DSH manager for user Skills already on disk in Agent home and DSH home
@dsh-enhanced/assistant-skills
Capture independently accepted tool workflows and replay versioned skills through the current native Goal and tool authority.
dsh-eteams
ETeams for DeepSeek Harness: captain-led multi-agent team collaboration with execution chains, task slots, member dialogs and persistent state
dsh-dingtalk-channel
DingTalk IM bot channel for DeepSeek Harness: each chat drives its own agent, replies and thinking come back as messages over the Stream-mode long connection.
@yadsh/dsh-answer-review-gate
Independent answer review gate for DeepSeek Harness agent responses
dsh-custom-subagents
Custom reusable Subagent Definitions with a Settings page and one delegate_agent tool for DeepSeek Harness
codsh-cli
A Claude Code-style coding agent for the terminal, composed on the DeepSeek Harness (dsh): interactive TTY surface, plan mode, approvals, custom commands, and session management over the dsh plugin runtime
dsh-lark-bot
把 DeepSeek Harness (dsh) 装进飞书/Lark 的 bot，扫码即用：dsh Web 可视化设置、流式卡片、项目工作区、并行任务、多角色 Agent、安全网守护。| Bridge DeepSeek Harness into Feishu/Lark with visual dsh Web settings, streaming cards, workspaces, parallel tasks, roles and a safety-net guardian.
@toddzheng024/dscode-desktop
Coding collaboration, memory, browser workflows and task management for Harness Desktop.
dsh-team-rooms
Retired: DeepSeek Harness now ships the native Agent Teams subsystem. This plugin remains installable for reference; use the native Agent Teams for new work.
@dsh-enhanced/assistant-evolution
Approval-gated behavioural self-evolution for the DSH personal assistant.
@dsh-enhanced/acp
Use DeepSeek Harness as an Agent Client Protocol (ACP) stdio agent.
dsh-run2skill
Turn explicit DSH session experience into reviewable native Skills
dsh-review
Packaged multi-agent adversarial code review for DeepSeek Harness — one finder per lens in parallel, then a verifier per finding whose task is to refute it, so only confirmed defects are reported.
dsh-my-go
DSH plugin: Sisyphus agent orchestration — star topology, single-line blocking, 7 specialist sub-agents (Hermes/Explore/Librarian/Looker/Hephaestus/Prometheus/Oracle) with per-type model binding, go_work/continue/need_help/forward communication tools, Web
dsh-subagent-codex-pro
A Codex delegation tool for DeepSeek Harness that can carry a model and a reasoning effort per call.
@dsh-enhanced/assistant-proactive
Owner-authorized goal event opportunity filtering with durable utility decisions and cooldowns.
agent-feedback-loop-dsh
Native DeepSeek Harness plugin: feeds every prompt into the local agent-feedback-loop capture pipeline and injects compiled recurrence rules back as context.
dsh-wecom
dsh-wecom: a WeCom AI Bot channel for DeepSeek Harness — each chat runs a persistent, preset-backed agent over the official long connection.
dsh-rev-eng
Reverse engineer anything and build any Mac app: REA and BAMA agent skills, packaged as a DeepSeek Harness plugin bundle.
@ran-sh/dsh-crew
@logictan/dsh-browser-agent
DSH browser agent: a dynamic operation+target decision loop. TypeSafe picks the action, this plugin executes it over CDP against the user's own Chrome. DSH 浏览器 Agent 子插件。
dsh-outer-brain
A philosopher's way of thinking made executable: dialectics and practice-testing to govern hallucination and long-session drift, so done is a verifiable fact rather than a claim.
@openma/dsh-agents-plugins-bridge
Portable Agent Plugins, Codex, Claude Code, and Pi plugin bridge for dsh
dsh-auto-classifier
Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance
dsh-plugin-coaligne
CoAligne team context for DeepSeek Harness: bundled coaligne-workflow skill for shared projects, synced files and Agent sessions; pairs with CoAligne Desktop, which auto-provisions the MCP connection
@dsh-enhanced/assistant-growth-driver
Bounded growth agent with durable reviews driven by owner-verified task feedback and frozen source models.
dsh-vision-subagent
Capability-aware vision for DeepSeek Harness: native image input for multimodal models, with an isolated one-shot vision-route fallback for text-only models.
dsh-skill-creator
Skill Creator: Teaches agents to write high-quality SKILL.md skills according to the agentskills.io specification (frontmatter, progressive disclosure, and trigger descriptions). Adapted from Anthropic’s official skill-creator (Apache-2.0).
