CATEGORY
Verified manifests and exact versions in this category.
dsh-astrbot-ingress
HTTP ingress that lets AstrBot drive DeepSeek Harness agents (OneBot / official IM via AstrBot).
harness-relay-mcp
Delegate and monitor DeepSeek Harness work from any MCP agent.
dsh-cohub
DeepSeek Harness CoHub: Chinese agent orchestration — users can choose between 2 work modes (co-orchestrator pure orchestration / cohub-cordis creative mode) + 13 specialized agent skills + multi-model consensus; additionally, the two supporting presets cohub-subagent-readonly / cohub-subagent-write
@morehao/dsh-commands
Integrate agent-skills' git-kit Git workflows, handoff cross-session handoff, and disk-cleanup disk cleanup as dsh-native slash commands (a thin intent mapping that delegates execution to the corresponding skills)
dsh-decision-engine
dsh-decision-engine: a cheap judgement layer for DeepSeek Harness — a small decision model answers structured questions before the main model acts, so calls can be allowed, escalated, rerouted to a cheaper model, or skipped. All eight decision points (too
dsh-requirements-alignment
Runtime requirement drift guard for DeepSeek Harness — keeps long-running agents aligned with user intent while they work.
@dsh-agentic-roleplay/core
Core plugin of the agentic roleplay bundle for DeepSeek Harness: roleplay UI, orchestration and storage.
@goodandready/dsh-agent-loop-guard
Fail-closed runtime tool-call loop guard for DeepSeek Harness.
@dhicoc/dsh-wuyun-liuqi
Five Movements and Six Qi (Yunqi theory) AI Agent skill package, packaged as a DeepSeek Harness (dsh) Cordis plugin: Heavenly Stems and Earthly Branches calculations, pathogenesis analysis, classical literature, interpretation of ideas, and self-evolution.
@weibaohui/dsh-thinktank
dsh plugin · Think Tank: Comprehensive analysis using mental models: includes a library of 161 classic mental models across nine categories (decision-making/strategy/cognition/psychology/communication/learning/systems/innovation/execution). Enter a question to have multiple selected models perform p
dsh-orbital-agents
Persistent Endeavour/Challenger ordinary-session peer runtime for DSH: durable plans, two-phase Challenger execution and peer navigation.
@dsh-agentic-roleplay/all
Agentic roleplay bundle for DeepSeek Harness. Install this one package to get every roleplay plugin.
dsh-expert
T Expert — a 636-expert, 22-division roster with full Chinese translations, as a standalone DeepSeek Harness plugin.
brooks-lint
AI code quality reviews grounded in twelve engineering books, with six portable Agent Skills for coding agents.
@skillroute/dsh-plugin
SkillRoute by JEStats: skill routing for DeepSeek Harness agents.
@alpacachen/dsh-automation
Durable agent-created automations for DeepSeek Harness
@double-coding/flow2spec-deepseek-harness
Native DeepSeek Harness plugin for Flow2Spec
agentschat-mcp
Connect Claude Code to AgentsChat — AI Agent social network. Core tools stay lean while extended tool groups load on demand for lower token overhead and cleaner role-specific context.
dsh-smart-restart
DSH host plugin that detects when the DeepSeek Harness service has restarted and wakes the main agent at boot with a notice, so interrupted work can be resumed.
evo-subagent
已迁移至 dsh-evo-subagent，后续更新请使用新包。Renamed to dsh-evo-subagent; use the new package for future updates.
dsh-autotier
Automatic strong/cheap model-tier routing for DeepSeek Harness: intent-gated tier landing on the agent/request waterfall, plan-mode handoff (strong plans, cheap implements), deterministic high-risk guards on tools/pre-execute, failure escalation with TTL
dsh-trip-planner-cn
DeepSeek Harness 插件外壳：把境内旅行规划 Agent Skill（trip-planner-cn）注册进 DSH 技能目录，装完即可按名加载 SKILL.md 及其 references/scripts/themes 资源。 / DeepSeek Harness plugin wrapper that registers the domestic-China trip-planning Agent Skill (trip-planner-cn) in the DSH skill catalog, with its bundled references/scripts/them
@tianbuyu-wwx/dsh-hermes-link
Bidirectional bridge between Hermes Agent and DeepSeek Harness. Hermes dispatches focused tasks via JSON-RPC over POST /mcp/collab (one-shot or continuable, nonce-bound amend, secret-bound consult reply); DSH lets you continue Hermes sessions as native DS
clearai-dsh
ClearAI: The Epistemic Loop, native to DSH.
dsh-decision-layer
A structured decision layer for the DeepSeek Harness agent loop: a danger-call gate, output self-check, tool narrowing, and loop guard backed by a pluggable adjudication model.
@jasonfreelab/dsh-superpowers
A DSH port of obra/superpowers — the full multi-agent software-development methodology (TDD, planning, debugging, review) as native DSH skills
dsh-subagent-profile
Dispatch one-shot subtasks to derived subagents with per-task overrides (preset/model/provider/reasoningEffort/persona/tool whitelist), a runtime-derived cost guard, a subagent-profiles service, observability metadata, and a web-GUI settings page plus a d
@yottameta/yotta-skills-plugin
YuanGe (元阁) — orchestration and routing for the YottaMeta skill family, packaged as a YottaMeta Agent Plugin and DeepSeek Harness profile bundle.
dsh-skill-tag
Tag DSH skills and use a single Boolean expression to select the subset of skills to send to the model at the workspace and conversation levels
dsh-agent-relay
Multi-agent collaboration relay for DeepSeek Harness — send and receive messages between local agents (dsh, Codex, Claude, Hermes, OpenClaw, …) through a small loopback-first broker with HMAC auth. Ships the broker, the dsh plugin, a CLI client and a Pyth
