Plugins

Host-side unattended job scheduler: runs one-shot agent tasks or shell commands on cron, interval, or one-time schedules, with persisted at-most-once dispatch state, overlap/misfire policies, and bounded run history.

Git-style conversation branching that mirrors how real programmers collaborate: a secretary root branch dispatches tasks to child branches with their own contexts, merging back only compressed summaries via squash or rebase; ships /branch commands, a branch tab, branch-to-branch messaging, and a governance baseline pairing each session branch with a git worktree.

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.

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

MCP server installer and verifier for DeepSeek Harness: interactive init writes real patch entries into a profile, list and validate inspect them, and a CI-enforced verifier connects to every curated server.

Kanban task board for DeepSeek Harness sessions: the main agent dispatches coding tasks to one-shot worker/verifier subagents, with dependency scheduling, pipeline tiers, escalation handling, and file/notes context injection.

Routes model requests, web fetches/searches and spawned tools through the Windows system proxy or a custom address — idempotent kernel (reads never rebuild the dispatcher), header one-click toggle, per-URL route diagnosis and NTLM-aware 407 hints.

Two-way sync of DSH sessions, workspace mappings, settings and patches between machines through your own private GitHub repo (API keys stay machine-local).

Named subagent roster: manage role entries (model, persona, tool filter, depth, background mode) from a hot-reloaded settings page; the model picks one with list_subagents and dispatches by id with delegate — foreground, background, or continuable.

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).

Installs an Orchestrator agent preset that plans and dispatches to model-pinned specialist subagents (explorer, oracle, librarian, designer, fixer, council), with named model profiles switched via an omoslim CLI and a Web inspector button showing the current subagent models.

Turns the 13 δ-me13 (Amphoreus) role skill cards into seat workspaces: per-seat theme and wallpaper, first-turn skill injection, chat stickers, per-seat memory notes and presets, Alt+digit seat switching, and an overview canvas for dispatch and handoff; the skill suite itself is read from a configurable local directory and is not bundled.

Multi-model orchestrator: the main brain decomposes complex tasks and dispatches subtasks to GLM / Kimi / Qwen sub-agents by each model's strengths, with per-model token usage.

Diagnoses and fixes "duplicate loader entry id" boot crashes - finds duplicate loader rows across profile bundles and converts them into id-targeted patches via a zero-dependency CLI (detect / preview / fix / verify).

Kimi-Code-style swarm: batch-parallel subagent dispatch with adaptive scheduling, a /swarm command, and in-chat live progress rows.

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

One repository that installs as both a Claude Code plugin and a DSH plugin: six engineering skills (research, architecture scouting, implementation orchestration, three-axis diff review, complexity audit, mutation testing) plus one agentforge tool dispatching five subagents.

Runs 3 or 5 coding-agent candidates in detached Git worktrees, validates their patches with project commands, ranks only passing candidates, and requires separate approval before applying the winner.

Visual development studio for DSH WebUI plugins with isolated Git worktrees, live official-WebUI previews, source editing, patch inspection, builds, and validation.

Plug/unplug any DeepSeek Harness plugin cleanly — list every mounted layer (bundles + patch rows), remove with full cleanup, disable/enable without deleting, and audit for orphaned/dangling state. CLI + agent-callable unplug tool. Read-only by default; destructive operations require explicit confirmation.

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.

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.

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

A minimal phone remote control for DeepSeek Harness: the phone page carries only the instruction you send and the AI's final conclusion, while tool calls, file access, sub-agent dispatch, and reasoning traces stay on the computer, reachable over LAN, Tailscale, or a Cloudflare tunnel with a QR code, link, and password for each route.