by BillyChen123

Question-Driven Discovery research workflow for DeepSeek Harness with a QDD Agent Preset, durable Human and Auto runs, and an auditable research panel.

by ZekaiShi

Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution (prefercmd/memory as knowledge allow/deny lists), so repeated tasks start from proven commands and save tokens. Unifi

by L3n3L

AI can write resume text, but templates may still look wrong, pages may overflow, whitespace may remain, and small edits can destabilize the layout. dsh-resume provides an end-to-end DSH workflow for

by lanbaolu

⛔ No longer maintained (2026-09-12): Fallback capabilities such as broken-plugin isolation are now built into DSH Desktop → Please use https://github.com/dataelement/dsh-desktop directly

by cofy-x

Scheduled tasks (cron) for DeepSeek Harness: model- and human-callable scheduling that fires followup/inject into agent sessions

by jerryjiao

WeChat Official Account AI writing plugin, running inside DeepSeek Harness: one command installs the full writing pipeline (topic selection → writing → quality gate → layout → illustrations → drafts). Scheduled posts go to drafts only by default; mass sends are always manual. MIT open source.

by MistyBridge

Multi-agent orchestration for DeepSeek Harness: turn isolated sessions into a team that assigns work, reviews output, and runs DAG workflows — durable task ledger, real reviewers, crash-safe recovery.

by kui123456789

DSH plugin that coordinates Codex planning and independent review while DSH executes.

by mjylfz

Adds a subagent_codex tool that delegates tasks to the local OpenAI Codex CLI, running the work in an isolated external process.

by thomasvvugt

Agent-driven kanban board for DeepSeek Harness: one board per workspace, per-task agent sessions, guarded human/agent workflow

by stuarthu

dsh plugin: run work as a small crew of role agents (product manager, researcher, architect, engineer, QA, code reviewer, security reviewer, doc reviewer) that share work through files on disk

by joekytc

Run multi-agent task pipelines on DSH like a team — plan, execute, review, and deliver code through a visual kanban with provable completion.

by MaRi23333

DeepSeek Harness Named subagent roster plugin: settings-driven subagent roster, list_subagents / delegate tools and settings page. Named subagent roster plugin for DeepSeek Harness.

by euuuuuuzer

A loop dock for DeepSeek Harness: one harness, multiple agent loops.

by moyu-good

🕊️ Run a full DeepSeek Harness coding agent inside Feishu/Lark — native thinking process (CoT), interactive approval cards, live reactions, slash commands, WS long-connection. No public callback URL.

by hanxuanliang

Durable multi-agent collaboration for DeepSeek Harness: channels, threads, tasks, and resumable agent sessions.

by lonelymoon87

Specification-driven development toolkit for DeepSeek Harness.

by alex04130

DeepSeek Harness Extension Suite: Runtime Injector, Sub-agent Dispatch and Model Routing Strategy, Plugin Marketplace/Skills/Plugin Management Panel, Browser Bridge and MCP Integration.

by muzyLink

DeepSeek Harness Sub-Agent Dispatch Plugin: selects the model, reasoning intensity, and tool scope for sub-agents based on each task; saves common combinations as named presets for on-demand reuse; includes built-in safety checks, cost estimation and savings analysis, and a complete dispatch decision ledger.

by geguanming

DSH Ox-Horse Office - a DeepSeek Harness web plugin rendering multi-agent sessions as a live pixi.js office

by Letter2025

Two-level model circuit breaker with failover for DeepSeek Harness: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback

by dsh-plugin-collection

Scheduled reminders and delayed send for DSH: /later delivers what you type as yourself at the time you pick, while the timer panel (or /schedule) posts a reminder row — even with the page closed. (sc

by 82c86b8z86-stack

Engineering workflow layer for DeepSeek Harness (dsh): a disciplined-engineer agent preset with five gated phases — requirements clarification, plan approval, TDD, parallel subagent execution, and ver

by cxv117793-blip

Counts agent steps and, every N of them, adds a progress-report instruction to the batch that is about to be sent, so the agent states what it is doing, what it finished and what comes next, then carr