The "subagent" topic on GitHub groups 62 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-auto-review with 198 GitHub stars. dsh-auto-review — Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided). Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.
Interactive long-session background agents for DeepSeek Harness: start a durable continuable child agent, watch its progress in the Web UI sidebar, message it any time, and interrupt it - all through the official subagent seam.
Auxiliary models for DeepSeek Harness: vision understanding and context compression through dedicated model routes. DeepSeek Harness auxiliary model plugin: provides independent model routes, tools and system prompts for vision understanding, context compression, approval review, sub-agents, session titles and image generation, never touching the main conversation model.
Agent-office dashboard for DeepSeek Harness (DSH): workspaces, sessions, token usage & subagents in a 6-column sprite office — plus Agent Mail, Feishu/Lark messages, meetings, transcripts & office logs. DeepSeek Harness "office" plugin: workspaces/sessions/tokens/subagents + mailbox/Feishu messages/meetings/transcripts/logs at a glance, see what every Agent is busy with.
DeepSeek Harness sub-Agent dispatch plugin: pick model, reasoning effort and tool scope for subagents per task; save common combos as named presets for reuse; built-in safety checks, cost estimation and savings analysis, full dispatch decision ledger.
A whale-girl themed subagent nest for the DeepSeek Harness, featuring pixel-animated subagent cards, real-time THINK/TODO tracking, and a model-selectable subagent_ex tool.
DSH plugin: sub-agent matrix swarm — routes heterogeneous tasks to the most suitable model (OpenRouter-like + cfgpu.com/llm/square), dispatches each via in-process subagents. 32/32 benchmark green.
DeepSeek Harness plugin: subagent_routed — run a one-shot subagent fully mounted on ANY agent preset from ANY session, with per-call model/provider override and a model-availability pre-check.
A minimal, opinionated subagent for DeepSeek Harness: you choose which models a child may run on and at which reasoning effort, and a correction reaches a working child at its next step
Multi-channel coding-agent subagents for DeepSeek Harness: Codex, Claude Code, Grok Build and configurable ACP agents, with strict roles and durable runs.
This plugin was developed using DeepSeek Harness and the DeepSeek V4 Flash 0731 / Pro 0813 models, with multiple rounds of refinement. It enhances the existing sub‑agent functionality and adds several other features.
DeepSeek Harness named subagent roster plugin: settings-driven role roster, list_subagents / delegate tools and a settings page. Named subagent roster plugin for DeepSeek Harness.
A read-only memory room for DeepSeek Harness: a scribe_recall tool over plain markdown, path-safety rules that refuse traversal, Unicode smuggling and NTFS alternate data streams, and an index that never truncates silently.
DeepSeek Harness (dsh) plugin: live token cost of every chat, its subagents and the whole session tree — DeepSeek, OpenAI, Anthropic, Gemini, Kimi, Grok and Mistral prices from a bundled catalog, plus an append-only JSONL cost log in your project folder.
DeepSeek Harness plugin: planner/executor separation — the main model plans, dedicated execution subagents do the work on a configurable model, managed from the Web settings panel.
DeepSeek Harness parallel multi-agent orchestration plugin - dispatch multiple sub-processes to run in parallel, main process can call in and revise anytime (AI-made, works decently)
Processes tab for DeepSeek Harness: every agent and subagent of a conversation as a live console with paired tool requests and responses, installed as one profile bundle.