Bundle
dsh-zentao-mark-effort
DeepSeek Harness bundle for ZenTao MCP, task/bug workflows, reports, and verified formal effort recording.
Browse
105 results
Bundle
dsh-reasoning-ruler
A minimal reasoning-effort ruler for the DSH composer: one hairline, a sliding marker, per-model memory, optimistic switching — and a streamlined model picker.
zisen123
Bundle
@bo_wu/dsh-reasoning
Codex-style /reasoning command for DeepSeek Harness Web: select the reasoning effort of the current model from the slash menu
BoWuGit
Bundle
dsh-task-effort
Auto-adjust model reasoning effort per task: off/low/high/max with task classification, peak-pricing-period capping, countdown notices, and in-turn error escalation
zhangzhenwen1
Bundle
dsh-agent-team-model
Choose default and per-name provider, model, and reasoning effort for newly created DeepSeek Harness Agent Teams teammates, with live team status and restart-safe route views.
XMeowchan
Bundle
dsh-plugin-reasoning-efforts
Grant official-style reasoning-effort selection to hand-declared pi-ai models (DeepSeek relays and the like) in the chat box
chuling-lingling
Bundle
dsh-effort-router
DSH Effort Router（模型分流）：按每一轮请求的难度自动选择模型与思考强度——简单问题走便宜快模型，难题才叫强模型。规则判定零 token，灰区交给一次小模型裁定，图片档强度随难度升降（low/high/max）。每轮请求级覆盖，不改你的会话选择与默认模型。
wanghaixu-hai
Bundle
@openplan/dsh-fuse
Cost policy for the DeepSeek Harness: per-call metering plus a local fuse that enforces budget, model and reasoning-effort limits before any token is spent.
openplancc
Bundle
dsh-custom-provider
dsh web Settings section (Custom models): subagent delegation allow-list, plus per-model image-input / reasoning-effort mapping.
homily707