Plugins

兰亭 CLI 命令工具化 + L0 守卫：记忆面 9 工具 + 质量面 6 工具（defineTool 注册，spawn venv _cli.py）+ 直写/直调守卫

Rules execution engine for dsh: parses AGENTS.md, hard-blocks rule-violating tool calls, text-based B/D rule auditing, /guard command, version-guard for versioned files, and free-zone support (engine skips free-zone sections).

Model-driven /init command: the agent analyzes the current repo and generates/updates a high-signal AGENTS.md, with a persistent system-prompt reminder to keep it maintained.

Tested-curation lab for DSH plugins: every entry passes real install/static-scan gates in an isolated environment, with full logs and reproduction commands (Chinese-first).

Multi-platform IM gateway for DSH: Feishu (Lark) WebSocket long connection (no public URL), WeCom AES-encrypted callbacks, and Telegram long polling — per-chat agent sessions, whitelist access, and a visual settings card in the web GUI.

Folio (兰亭) @nyantused/folio-dsh-tools: 15 schema-validated tools (memory + quality gates) plus an L0 guard of the consulting document-generation engine; pair with @nyantused/folio-dsh-events for the full session protocol.

Folio (兰亭) @nyantused/folio-dsh-events: session-protocol events — auto session-start reminder + auto-save on session close; pair with @nyantused/folio-dsh-tools.

A structured multi-panelist review workflow for the DeepSeek Harness: N panelists score in isolated subagents, blind to each other; a chair reconciles disagreement by anchor match then Δ-level adjudication; an independent critic audits the process. Works for design, code, paper or project review.

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

Docker tools for agents: ps/images/logs/inspect/exec/manage/health with JSON output, env-configurable CLI path, approval-gated exec and zero runtime dependencies.

Lets sandboxed agents reach the web through your local proxy: net_fetch fetches pages, net_proxy_status reports proxy status.

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.

One toggle makes the whole DeepSeek Harness shell translucent, with an opacity slider and a custom full-page background.

Shows DeepSeek API account balance and Volcengine Ark Coding/Agent Plan quota windows (5h/weekly/monthly with reset countdowns) in the settings panel, composer dock, and a draggable floating refresh button.

OpenCode Go plan usage display for the DSH web GUI: a persistent badge under the composer shows rolling/weekly/monthly usage percents with reset countdowns; click to expand a card; agents can query the balance via the `opencode_go_usage` tool.

Adds a Desktop card to the settings page that detects the DeepSeek Harness Desktop app and launches it with one click.

Diagnose, unstick, and read DSH sessions: list sessions with agent status, read conversations, diagnose stuck agents, recover them with cancel+keepInbox, and send messages to other sessions.

DSH port of TaskPlane: dependency-ordered waves run in parallel git-worktree lanes, with task packets, cross-model review, and crash recovery.

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

Opens a separately downloaded Windows desktop pixel monitor for pi, Claude Code and DSH sessions. DSH monitoring is read-only.

A slim tool strip beside the conversation: one-line notes into a sticky note, a follow-up or a reminder (the sticky-note and follow-up modes need the dsh-sticky-wall and dsh-followup plugins installed); selected text quoted, saved or handed to the model; saved prompts into the composer in one click; a recap of this thread or the previous one; a read-only panel for context use, tokens, subagents and open follow-ups; plus custom entries that open a path or run a command.

DSH SMOOTH: config-only bundle for a lighter DSH UI - compact transcript and usage views, 16 px font and 200 ms job polling out of the box - plus a troubleshooting SKILL.md and opt-in recipes (appended by hand to your own cordis.patch.yml or the profile) to remove the Agents-Anywhere "Reconnect" button, slim the tool list, drop legacy sub-agent bundles and make compaction thresholds take effect. User patches still win; rollback = remove the bundle.

Picks each subagent model from the local catalog by task category, unless the caller already named one. Free and quota tiers are ranked together by per-model capability tags; a pricier model is used only when no cheap model is tagged as good at that kind of work. Only providers whose remaining balance is readable, or that are account-backed, enter the candidate pool; the rest stay listed but are not routed. A panel adds per-model manual priority above the automatic order plus allow/revoke controls.