DSH插件商店

Vibe-Skills

foryourhealth111-pixel

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

dsh-token-optimizer

Zoria-Lind

Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.

agent-body

1420079678-ctrl

Gates 84.7% of tool-schema prompt tokens away for DeepSeek Harness: plugins declare themselves organs, a nerve impulse routes each command, reflex arcs fire with zero model calls, memory consolidates while idle, every failure is attributed before retry. Reproducible offline, MIT.

evo-subagent

ZekaiShi

Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution (prefercmd/memory as knowledge allow/deny lists), so repeated tasks start from proven commands and save tokens. Unified subagent routing and evolution: prefercmd/memory serve as knowledge allow/deny lists, saving tokens.

dsh-workspace-mover

PianoPrince

拖拽真迁移 DSH 会话跨工作区：批量移动、分组合并、挂错归位、回收站、备份恢复 + 对话内 agent 工具；步步备份可回滚，零 token / True migration of DSH sessions across workspaces: bulk move, group merge, misfiled homing, recycle bin & backup restore + conversational agent tools; every step backed up, zero tokens

mnemon-memory-agent

Grivn

Long-term memory for AI agents on Jev. Keep raw records, judge them with a fast System 1 model and answer from under 4k tokens of context.

dsh-stepwise-distill

yunxiyang

Solidify DSH session history step by step: rewrite tool results in place to the facts the model actually kept, so long conversations stop re-sending noise every turn. Costs tokens and time: a ~770-character contract in every request, plus one extra full-context request and round-trip per step when stepSummary is on.

s1cap

Jaffe2718

System-1 decision models (Jev/Laya/Kev-class) as the governance layer for an LLM agent context lifecycle: growing association graph over session segments, relevance-gated recall with Trace-as-State ordering, and plan pre-ranking — measured in solve rate, cache hit/miss tokens, cost and latency. DSH plugin + harness-agnostic proxy.