Plugins

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

Ecosystem infrastructure: a thin browser console for managing official repository plugins (zero patches) plus a make-dsh-plugin skill for guided plugin development.

Plugin health checks: manifest protocol / patch format / build traps, zero-dependency and read-only.

Modifies DSH plugin code at runtime, with ordered patches, inspection, and hot reload.

Read-only runtime management panel for the official DSH MCP client: connection status, registered tools, errors, and reconnect counts through the /mcp command and a Settings tab, with sanitized display and enable/disable patch suggestions.

Hook DeepSeek Harness into a Hermes pipeline: dispatch-spec template, model-tier routing, orchestrator-run quality gates, git single-writer rule, as a SKILL.md pack (bundle installable).

Installs a multi-agent novel-writing preset for DeepSeek Harness: one conductor agent dispatches five specialized subagents — world-building, plotting, character management, prose writing, and QA review.

OAuth / subscription-plan LLM login (Grok, GitHub Copilot, OpenAI Codex, Anthropic, OpenRouter): durable credential store with on-request token refresh, no repo patches (Grok/Copilot verified; use Codex with caution).

Health checks for DSH plugins: manifest/patch/entry/build/pack/install verification, model-callable plugin_check, profile host-shadowing + BOM detection, environment diagnostics, and poison preflight.

A settings-panel skin manager that auto-discovers installed Web UI skins, switches between them in one click, and maintains the profile patch automatically.

Extends dsh-subagent-tools with a per-call cwd for subagents, shipped with the two in-process provider patches it requires.

Sidebar file tree for DeepSeek Harness: a files panel with a lazy, per-extension-icon tree, copy-path and send-to-agent actions

Linux kernel dev domain plugin for DeepSeek Harness (dsh): verification pyramid L1-L4 as model-facing tools + graph-layer governance (anti-Goodhart / blind-spot / patch-conflict) + AGENTS.md contract as a system-prompt section. Plain JS, no build step.

Unified DeepSeek Harness connector: edit MCP servers (cordis.patch.yml) and user skills (~/.dsh/skills) from one Web UI settings page.

Config-driven lifecycle hooks: event→command declarations in cordis.patch.yml, with Feishu card notifications and a QR scan-to-create bot setup.

Self-editing desktop workbench for DeepSeek Harness: a full dsh web replica with an edit mode in which the agent modifies the workbench (patch layers, plugins, UI) with hot reload.

Read-only health clinic for the installed DSH plugin set: loader health, dependency integrity, version compatibility, install-script risk, duplicates and patch integrity, delivered as a model tool, a Settings dashboard and JSON reports.

Registers `list_profiles` and `export_profile`, so the agent can show what setups exist and hand back a whole profile — bundle order, plugin versions and patch — as one portable file to share. Read-only.

Registers a `config_doctor` tool that checks the harness's own configuration for problems that boot silently: fields a patch dropped by whole-config replacement, patches targeting missing entry ids, and tool-name collisions. Read-only.

Dispatch self-contained tasks from DSH to 11 external agent CLIs (Codex, Claude Code, TraeCode, OpenCode, Gemini, Cursor, Kimi, Qwen, Copilot, WorkBuddy, Grok): a host-only bundle registering the conductor_dispatch tool plus an auto-triggered conductor skill.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.

Auto-repairs the messages array after a tool-dispatch crash (orphaned tool_calls / tool messages), preventing 400 INVALID_REQUEST session lock-ups.

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

Interactive terminal chat app for dsh: streaming conversation, tool cards, jobs panel, full-text search, trajectory replay, multi-session tabs, and A2A dispatch (Ink-based).