DeepSeek Harness Plugins · Workflow
Plugins that extend DeepSeek Harness (DSH) with vision, workflows, memory, web tools and more.
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.
Persistent, reusable multi-model Agent teams for DeepSeek Harness, with per-member model, role, tool policy, fallback routes, bounded DAG orchestration, quality gates, and a Run Center.
Preview a bounded five-part handoff before migrating a DSH session: /bridge opens a clean target session, leaves the original untouched, and adds zero prompt tokens as a host slash command.
Installs the Minimal (Git Bash) agent preset for DeepSeek Harness, auto-detecting Git Bash and running each command via bash -c so minimal-mode bash becomes usable on Windows.
A standalone DeepSeek Harness plugin that adds composable workflow controls for work state, thinking strategy, quality gates, and agent self-evolving.
Dispatch work to DeepSeek Harness agents from Claude Code, Codex, Antigravity, and Grok as native subagents, with tier policy, escalation, dispatch guardrails, a jobs board, in-host sessions, and vision/image generation.
Upgrades DeepSeek Harness one-shot multi-Agent scheduling into a workflow layer that is generatable, saveable, governable, observable, and resumable, as an official bundle-style plugin with zero core patches.
A local-first A-share research workbench built on DeepSeek Harness, covering the full pipeline from market overview, watchlist valuation, and K-line analysis to master-method judgements and open expert conversations.
Run coding tasks on schedule from Web or Agent, with fresh isolated sessions and auditable run history.