by yixing233

CrabTodo - persistent todo plugin for DeepSeek Harness: model-facing todo tools + web sidebar page. Persistent todo plugin: model tools + Web sidebar.

by OTTTTTO

Scheduled send: fire a drafted message into the bound conversation as a normal user bubble at a set time. Runs host-side, so the browser can stay closed; per-session isolation and restart-safe redeliv

FIST commander task orchestration as an MCP server: seven-state task lifecycle, hierarchical decomposition, DAG scheduling, self-driving loops and Omega verification, all in one SQLite ledger. Ships a

by aorucshiea

Optional mid-session agent-preset switching: /preset command with a settings toggle, Web popup picker, and status API

Settings page for agent modes (presets): switch up to 15 capabilities per mode (commands, files or read-only files, web, subagents, and more) or individual plugin rows; edit each mode's system prompt

by zhengjy01

Cubox sync for DeepSeek Harness: scheduled sync of your bookmarks, an AI daily brief generated from your own prompt template straight into Obsidian, and per-card markdown export.

Model switching, model capability configuration, fixed compaction models, subagent routing, and input history enhancement.

Dual-brain agent presets for DSH: one model plans the framework and delegates execution to a subagent pinned to a second model. Ships brain-ds (DeepSeek-V4.1-Flash plans, MiMo-V2.6-Flash executes) and

Runs one-time and recurring Agent tasks in fresh DSH sessions, with natural-language schedules, visual schedule editing and session-linked history. Supports custom models, skills, pause on failure, an

Think tank: a built-in library of 161 classic mental models (decision/strategy/cognition/psychology/communication/learning/system/innovation/execution) — enter one question and several selected models

by HeliosTangDev

Injects a very short conventions reminder (absolute INDEX path + version) once per session per version; when the conventions version changes, the next turn re-injects it (chat turns included). Optiona

Visual Kanban board for DeepSeek Harness with Gitea-backed tasks, workflow columns and a dedicated agent session per task.

DevFlow multi-agent workflow orchestration plugin for DeepSeek Harness

Recurring task scheduler with an append-only delivery ledger: window-aligned dedup execution, failure/abandoned rows, and same-window retry redelivery.

by JessenReinhart

Port of jcode's auto-poke incomplete-todos feature as a Cordis plugin for DeepSeek Harness.

by Z-Asset

ZA Research literature stage — search, synthesis, and citation-chain tracking for asset pricing + ML/DL research.

Exposes the Paper-gogo evidence-first paper workflow as native tools: all 18 phases and the seven G0-G6 gates become callable, gate results are normalised and advancement is refused while any gate fai

Generic monitor plugin for DSH Desktop: an HTTP polling rule engine. Poll any endpoint on schedule (multi-step, variable extraction, JS condition expressions); when conditions hit, wake a visible agen

Workflow tools for the local aflare binary: generate, validate and run local-first deterministic YAML workflow DAGs (WAL crash recovery, Saga compensation) through the local aflare binary, with 300+ t

Parse PRDs and PDFs, ask clarifying questions in batches, consolidate a BRIEF.md system brief, and package deliverables for upload.

Jimu (积木): domain-based orchestration plugin for DeepSeek Harness — domain_plan confirmation, per-domain sub-agents with hand-off, and automatic LLM audit.

by nuaaweixinye

GME Test Agent workflow tools for DeepSeek Harness (dsh): pick interfaces, generate and repair tests autonomously in a local Python backend, poll until review, decide with consent.

Exposes bounded Prometheus metrics for DSH sessions, agents, LLM calls, tools, approvals, subagents, and jobs, with a Grafana dashboard and a loopback-only endpoint by default.

All-in-one UI enhancement layer for DeepSeek Harness web: prompt library with quick-insert and management, two-step AI polish, predicted-reply dock with click-to-send, MCP tool management, scheduled a