플러그인

Runs one coding prompt across multiple configured models in isolated Git worktrees, streams side-by-side tool traces and results, and commits the candidate the user adopts for later rounds.

自动标红思考过程中的let_me

Use OpenCode models inside DeepSeek Harness without a separate provider API key.

Schedules workspace Agent runs in fresh Result Sessions with persistent audit history, using a stock DSH Conversation tab or a global Shell page when its slots are available.

DeepSeek Harness (dsh) plugin: /refine command + settings panel for the dsh-continual-harness self-refinement engine — entry browsing, refinement history timeline, one-click rollback, auto-gate audit; engine optional at runtime.

怀疑驱动开发：每个非平凡决策在落地前接受新鲜上下文的对抗性审查（CLAIM→EXTRACT→DOUBT→RECONCILE→STOP）。受 addyosmani/agent-skills（88k★ MIT）启发。

Local tool-call failsafe for DSH: blocks a fixed list of high-risk shell patterns and credential-file reads before execution, with a per-session hash-linked JSONL audit log, and an optional external Gateway for centralized policy.

grok-style terminal UI for DeepSeek Harness — whale edition

Reports the semantic blast radius of agent code edits: which symbols changed, who calls them, and which of those callers have no covering test.

DSH 全局记忆插件：侧边栏「全局记忆」页，直接查看/编辑 ~/.dsh/AGENTS.md 与 ~/.dsh/memory/*.md。Host 半边注册 /api/dsh-memory 路由（回环限制），client 半边注入侧边栏入口与中心面板。热插拔挂载，不改 DSH 源码。

Kun Like 桌宠 · DSH 正式插件包：Web 界面右下角的坤宠，随 Agent 工作状态切换动作，任务完成时播放「你干嘛~哎哟」。作为 profile 插件挂载，重启仍在、所有会话页面共享。

DSH plugin: expose Trae Work CN credits as a local OpenAI/Anthropic compatible API for Claude Code, Cursor, Cline and other agents

Hold a DeepSeek Harness agent to a capmark capability manifest: mask its tools and judge every call.

ChatGPT-style conversation-history rail for the DeepSeek Harness web GUI: a strip of bars at the transcript's right edge with a hover panel listing every user message, click-to-jump and scroll-synced highlighting.

Clustr Trading Console for DeepSeek Harness: secure, multi-exchange tools and an AI trader cockpit.

上下文工程：按层级（规则文件→规格→源码→错误输出→对话历史）主动策划 agent 看到的信息，提升输出质量。受 addyosmani/agent-skills（88k★ MIT）启发。

Host-only peer session relay tools for DeepSeek Harness

Multi-agent orchestration for DeepSeek Harness. Sessions in one workspace assign work, review results, and run DAG workflows — without you as the messenger.

LLM API rate limiting, concurrency control, queuing, and adaptive cooldown for DeepSeek Harness

每日 AI 资讯 Agent 插件：日报(存70天)/周报/月报 · 结构化生成(合并提示词) · 真实web搜索 · host+client 双半面

Multi-server SSH terminal panel for the DSH Web GUI: floating terminal window with tabs, side-by-side groups, broadcast, host-owned persistent sessions, and password/private-key/SSH-agent auth.

Honesty guardrails on the tool pipeline: blocks a coding agent from weakening tests, swallowing errors, stubbing type checks, or deleting tests through the shell — nine deterministic hooks, each backed by a planted-failure test proving the guard can fail.

First-run health check for DeepSeek Harness: verifies Node/pnpm/dsh toolchain, home, profile, API key (names only, never values), workspace writability and npm registry, then prints actionable next steps — CLI plus an agent-callable quickstart tool, dsh-firstrun/v1 reports, zero runtime deps.

Persona wardrobe for DeepSeek Harness: save multiple personas, apply them globally or per workspace, with a master switch, an adjustable API balance guard, and a lazy token-loving tired mode that speaks on the agent's behalf when quota runs out. Files-as-config, hot reload, zero dependencies.