实时扫描最新社区关于 DeepSeek Harness 发布的插件

Completion evidence gate for DeepSeek Harness goal-mode subagents

Long-task gatekeeper for DeepSeek Harness: detects one-shot mammoth requests, asks whether to plan first, and scaffolds plan.md + a capped goal before the agent starts

Automatic cross-session GoodMemory recall and writeback for DeepSeek Harness

Governed long-term memory core and DSH technical-preview adapter contracts.

DSH（DeepSeek Harness）优雅重启/关闭/启动守护插件：启动方式不变（dsh web），自动套壳拉起正式实例；等轮次结束后优雅重启并唤醒智能体继续；启动失败自动回滚新增插件（多版本成功基线、官方 CLI）；页面自动刷新；设置菜单可调快照版本数。

DSH bundle: grok-geo GEO brand audit agent skill — AI-search visibility, recommendations, citations, competitor presence and content-gap diagnosis across 17+ AI engines (ChatGPT/Perplexity/Claude/Gemini/豆包/DeepSeek/Kimi/文心一言...), shipped as a bundled skill provider. Zero-dependency.

Agent 安全护栏：拦截并审计所有工具调用，命中敏感操作就要求人工确认

DeepSeek Harness task-protection plugin: plugin preflight scanner (catches missing `inject` declarations that crash the host), loop detection (repeated identical tool calls -> steer to a new approach), recursion guard (nested subagent depth cap), and interruption awareness (status route with safeToRestart). Never terminates tasks — only steers via injected messages. Zero npm dependencies.

My Habits for DeepSeek Harness: edit the user-global AGENTS.md from the Web settings — injected into every session by the built-in agent-instructions loader.

Hash-anchored read/replace/undo tools for DSH. Every line of a file carries a unique 3-char content hash; edits target hashes, never line numbers, so stale anchors are caught before they touch the file. Port of pi-hashline-edit-pro for the Pi coding agent.

Report DeepSeek Harness agent activity (working / blocked / idle) to the herdr pane hosting this dsh process

Environment housekeeper for DeepSeek Harness: toolchain inventory, agent scratch/cache scan with safe one-click cleanup, and the machine rules file (AGENTS.md) view/edit - all in the Web GUI settings. Zero runtime dependencies.

Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。

Give DeepSeek Harness agents the ability to read images directly: a model-facing read_image tool that answers questions about an image through any OpenAI-compatible vision endpoint.

A green interrupt button beside the DeepSeek Harness send box: silently stops a running agent, which then summarizes its progress and asks for your new requirements; the interrupt prompt is customizable.

Jina AI tools for DeepSeek Harness: search (incl. arxiv/ssrn academic domains), read, screenshot, embed, rerank, classify, pdf, expand, datetime, primer — with a settings-page API key UI.

K12 capability substrate for DeepSeek Harness: 143 objectively-decidable capability anchors and 6,091 list items extracted from China's MOE 2022 curriculum standards, with local-only learner profiles

DSH ↔ Hermes 双 Agent 协作管道的看板执行侧插件：监听 Hermes kanban 队列，把任务交给 DSH Agent 在 Web GUI 会话中执行，并把结果回写看板与 done 文件。 支持会话继承（[会话继承:关键词] 续接历史会话）。

DeepSeek Harness 批量并行子 Agent 调度插件：swarm_batch 工具（Kimi Code Swarm 模式移植）+ /swarm 命令 + 聊天内实时进度条。

Password + CIDR gate for DeepSeek Harness web / DeepSeek Harness 局域网密码门禁

Find DeepSeek Harness plugins, verify what they implement, and identify missing capabilities.

dsh-langfuse: Langfuse LLM observability for DeepSeek Harness — one OpenTelemetry trace tree per agent session, with feedback scores and subagent lineage.

Bridge DeepSeek Harness (dsh) into Feishu / Lark with streaming cards, project workspaces, approvals and scheduling

Real-time code feedback for DeepSeek Harness — LSP, linters, formatters, type-checking, and structural analysis.