Keeps an unattended DeepSeek Harness session moving when nobody answers ask_user_question: it fronts the question waterfall, leaves a human answer untouched, and after a configurable window (120 s by

Match your models and token budgets to each role, then let DSH delegate specialized subagents by task type. Covers architecture analysis, UI/UX, code implementation, codebase exploration, and document

by yezitotempeace

Agent Teams roster plugin: newest-first ordering for the roster, task board and subagent catalog, plus bulk cleanup and teammate rename/delete.

by Z-Asset

PPT stage — presentation generation (Beamer/Quarto) from the paper for asset pricing and machine learning research. Ships one skill.

by xiagaogaozi

Maintains reusable named subagent profiles for DeepSeek Harness and runs them with per-profile model, reasoning effort, and agent-preset settings.

by nilesh32236

Cross-workspace AI worker fleets for DeepSeek Harness: spawn named worker sessions in other projects, queue or steer tasks into them, watch them in the background, collect their reports, and answer their escalations — all from one orchestrating chat.

Keeps a repository's task ledger as a resident prompt section with eleven native tools, plus a sidebar panel and a floating window for browsing the queue and signing off review tasks.

Discover and verify portable RoleHub roles, pin each exact bundle, then launch its prompt and bundled skills in an isolated, continuable DSH Session with Host-approved tool bindings and optional Agent

Unified anchored agent preset for DeepSeek V4 Pro/Flash on the official API and opencode-go: Minimal-exact two-tool first-request bootstrap, model-aware Pro/Flash paths, and epoch-aware catalog manage

Pre-visit due diligence and company research in DeepSeek Harness for customer background checks and risk briefs, with Qichacha MCP tool-call budget approval and entity confirmation.

Zero-token scheduled script runner for DeepSeek Harness (dsh-plugin): cron in the Host, no model calls, wake-on-change

AlphaRSI — three-role self-improvement loop that evolves the training recipe of alpha sequence models. Operator runs walk-forward, Evaluator grades with OOS RankIC, Refiner proposes hyperparameters vi

Explicit model routing for Main, Subagents, web_search, and image generation, plus a catalog-driven Composer and Plan Review picker with Model, Effort, Context, Fast, and Thinking variants.

by lion231226

Verified-progress ledger for long-running DSH work: an independent verifier certifies each claimed step, and a fingerprint check voids any verdict whose verifier mutated the workspace.

by advance-lion

DSH Plugin Installation History: Local record-keeping, organization by device, cross-device synchronization via Baidu Netdisk, and batch reinstall via checkboxes

Group-chat multi-agent orchestration console for DSH: autonomous decision-making, task dispatch, verification and iterative optimization for long tasks; bundles its own backend, installs with `dsh plu

One-click prompt polisher for the DSH composer: a ✨ button next to the message box opens a side-chat where an agent refines your rough draft over multiple turns, then you copy the result back. Replays

by 7bder

Read-only orchd panel for the DSH right sidebar: task board, ideas board, dependency graph, review timeline and an install entry for the project of the current session.

by Missher12

Scoped project task discovery and execution receipts for DeepSeek Harness

by WaldInsel

Let external agents collaborate inside your existing DeepSeek Harness desktop, with visible sessions and human control.

by Saretheya

Session-local scheduled tasks for DeepSeek Harness: inject a prompt into the current session after a delay, at a fixed time, or on a repeating interval — with a Web management panel, a /schedule command, and model-facing management tools.

by sxwer001

DSH native collaboration: main-agent architecture and validated plans, parallel workers, verification and independent review.

Pair a second model that passively reviews each turn and injects notes.

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics,