Plugins

One memory layer for every AI tool and agent: Context Bundle injection, prompt-time recall, MCP tools, and turn-end DSH thread capture.

Carry durable task state across DeepSeek Harness, WorkBuddy, Claude Code and Codex with machine-readable checkpoints and optimistic locking.

Cross-session agent-to-agent messaging for DeepSeek Harness — address another session by name and deliver a message into its inbox.

Safe OpenAPI 3.x discovery and API calling tools for DeepSeek Harness

Plugin marketplace for DeepSeek Harness — live-syncs the GitHub dsh-plugin topic (1800+ repos) into a searchable, paginated settings tab with one-click install and agent tools (market_search / market_install).

DeepSeek Harness Telegram mobile remote: bind live Web sessions (Codex-style). Install: dsh plugin add github:hi-wenw/dsh-telegram-channel

DeepSeek Harness plugin bundle: graphlint dead-code detection tools for agents (graphlint_query / graphlint_build / graphlint_config + graphlint skill).

A desktop pet plugin for DeepSeek Harness (DSH): import Codex-style sprite-sheet pets and render them in the DSH Web GUI as a floating shell.overlay, with a pet library, interactions, and Agent-state linkage. / DSH 桌面宠物插件：导入精灵图序列帧宠物并在 Web GUI 悬浮渲染。

Evaluation harness for DSH plugins: YAML cases drive real headless agent runs, assert on tool calls, args, results and token usage, with a baseline gate for CI regression.

Appends local hash-chained JSONL receipts for tool results and session events without storing prompts, tool arguments, result text, or raw session IDs.

Writes local JSONL summaries of per-turn tool counts and coarse verification signals without storing prompts, tool arguments, or result text.

Automated unit-test generation: a /testgen command and generate_tests tool that scaffold, run, and fix tests until they pass (LLM + offline template generators; vitest/jest/mocha/node:test).

Fail-closed Feishu (Lark) channel bridge: chat with a bot, get dsh agent turns back. Official-Python-SDK-only integration (exact-pinned); deny-by-default allowlist, webhook signature/timestamp/replay verification, per-chat sticky sessions; bilingual docs.

Plan review with anchored annotations and structured feedback back to the agent.

Continual self-evolution: versioned, auditable, rollback-safe harness state (prompts, memory, skills, subagent specs) refined from session trajectories, with review gates and hot-reloaded skills.

Android GUI Agent with ADB screenshots, compact UI hierarchy grounding, verified iterative actions, approvals, and a Mobile Web view.

DSH↔Godot engine runtime bridge: launch and drive a running Godot 4.x game through its in-game TCP interaction server — 8 tools (scene/UI inspection, GDScript eval, input simulation, screenshots, headless static ops, script validation), replaces godot-mcp.

OpenCode Go quota ring: click-to-cycle progress ring (5h/weekly/monthly) left of the model selector, colored by urgency, with reset countdowns on hover.

Progressive-disclosure MCP gateway that searches large remote catalogs through `mcp_search`, then invokes exact schemas through `mcp_call` with lazy connections and bounded caches.

Codex-style drag-drop: drag any file into the DSH web GUI, it lands in ~/.dsh-dropbox, and the path is inserted into the composer as a whole blue chip.

让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度，并可为每次子 Agent 调用选择模型｜Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

Content-addressed artifact, fact, action and report lineage for DeepSeek Harness

DSH book-to-skill plugin: a 5-stage long task (fetch → parse → understand → generate → install) with 3 human gates, host tools for the agent and a browser timeline panel