dsh-plan-and-execute
dsh plugin: plan-and-execute orchestration over ReactLoopAgent
266 results
dsh plugin: plan-and-execute orchestration over ReactLoopAgent
DSH web plugin: play a chime when a turn completes or your input (approval / question / plan review) is needed — foreground or background.
ICPC competitive programming training tools for DeepSeek Harness — sync, analysis, plans, reviews, templates
Evidence-backed engineering Mission governance for DeepSeek Harness
DSH plugin: mint issue tracking integration — session context injection, event reminders, plan binding, a zero-approval `mint` tool, and a session tab.
External Agents control plane for DeepSeek Harness Product Workers
Independent DSH usage and plan-quota plugin with official provider windows, CLIProxyAPI aggregation, and a current-model composer strip.
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.
MxPage for DeepSeek Harness: ecommerce product-image workbench (analyze → plan → Visual Prompt Agent → generate) on top of an extracted, host-agnostic core of ziguishian/MxPage.
DSH refactor-insight skill plugin: turn codebase smells into an executable, priority-ordered refactoring plan (file-length, long-function, deep-nesting, god-object, high-coupling, and TODO-density heuristics plus a staged runbook).
dsh plugin that turns the iterate skill into an autonomous closed-loop harness with quality command center and experience bank (v3.3). Features: plan -> parallel review xN -> atomic fixes -> validate -> loop -> auto-stop, plus dry-run pure-review mode, qu
Plan and execute Atlas Cloud image, video, audio, and 3D workflows in DeepSeek Harness.
Host-plane kernel mesh for DeepSeek Harness: kimi/grok/codex/minimax kernel adapters, L2 subagent recipes, and kernel tools.
OpenGame browser-game planning and building Skill for DeepSeek Harness
Bridges the four z.ai GLM Coding Plan MCP servers into DeepSeek Harness via the in-box @deepseek-ai/dsh-mcp-client: vision (GLM-4.6V stdio via npx @z_ai/mcp-server), web reader, web search prime, and zread repo MCP (streamable-http at open.bigmodel.cn)
Education toolkit for DeepSeek Harness agents: lesson-plan skeletons, quiz validation, question scaffolding, analytic rubrics, grading sheets, study plans, class statistics, flashcards and readability levels
Multi-provider usage monitor for DeepSeek Harness: per-provider balance / token-plan usage card in the sidebar footer (above the Settings button) plus a「用量监控」settings section for per-provider special config (cookies, API keys), persisted in settings.yaml.
DeepSeek Harness plugin: LLM model selection & deployment analysis (deployability, VRAM, TTFT, latency, throughput, power for 38 models × 20 GPUs/NPUs)
DSH-native multi-runtime baseline, ablation, and reproducible evaluation control plane
LAN access layer for DeepSeek Harness (dsh) web — one-command install, default password 123: crypto.randomUUID polyfill for plain-HTTP LAN, a password login gate, a client isLoopback patch so the settings plane works on LAN pages, and password management from 插件配置 (zh/en).
Local-first AI teaching workspace for DeepSeek Harness — context, unit packages, assessment diagnosis, and next-lesson feedback loops
常驻 API 用量监控:DeepSeek/GLM Coding Plan/OpenCode Go/火山 Coding+Agent Plan 余额与配额,会话树 token 与花费(侧边栏入口 + 独立浮动窗)。
空间规划
家庭保险配置