Seven agent-preset modes for DeepSeek Harness, each with a fixed tool boundary, per-mode model routing and fast/deep omd_task delegation tiers, plus a plan-to-execute loop (/mode, /start-work, goal-backed /ulw) and a settings page that remaps models per mode and per tier.
- GitHub stars
- 5
- License
- MIT
- Added
- 2026-08-29
GitHub info
- GitHub stars
- 5
- License
- MIT
- Primary language
- TypeScript
- Last push
- Aug 29, 2026, 8:05 AM
- Maintainer
- jiazz197-cmyk
- Added
- 2026-08-29
Install
Install command
dsh plugin --profile web add github:jiazz197-cmyk/omd-dsh#path:/packages/omd-dshREADME badge
Add this Markdown to your plugin README to link back to its listing.
Listed onDSH Get
[](https://dshget.com/plugins/jiazz197-cmyk/omd-dsh%23packages/omd-dsh)Related plugins
Workflow & Automationouroboros#integrations/dsh-plugin
★ 5727Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.
Workflow & AutomationQ00
dashi-taskboard#deepseek-harness
★ 2741Embeds the active installed Codex Taskboard runtime in the DeepSeek Harness sidebar, using its launcher runtime descriptor instead of a fixed port.
Workflow & Automationchuspeeism
dsh-agent-teams
★ 1192AgentTeams multi-agent teams.
Workflow & AutomationNanmiCoder