Plugins

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

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.

PDF parsing tools for DSH: pdf_info, pdf_extract_text, and pdf_render_page with dual pdfjs and built-in rendering engines, including system-font rendering for PDFs with non-embedded CJK fonts.

JSON Schema validation: validate/paths/explain/normalize.

Export the current session to portable, schema-versioned Markdown and JSON files via the `session_export` tool and slash commands, with cross-platform-safe filenames.

Fronts stdio MCP servers with three router tools (list_capabilities, describe_tool, call_tool) so schemas load on demand instead of riding every request; shapes every tool result through a deterministic output ladder that archives the original first (retrieve_spill reads it back); prices tool groups in tokens and can hide built-in groups per agent. Bridges to a standard-library Python router, so Python 3.9+ is required.

Modellix integration for DSH: schema-driven image, video and audio generation in a split Design workspace, a live LLM model catalog, and native web search and fetch providers through one API key.

Natural-language data queries + BI reports: Text2SQL, charts, report saving, schema/data grid panel, and a sidebar workbench — all behind DSH's MySQL connection layer.

Safe, audited SQLite/PostgreSQL/MySQL access for dsh agents: schema introspection, enforced read-only queries, a write approval gate, and a durable JSONL SQL audit trail.

Prunes the tool schema to a whitelist and injects a structural preamble on a session's first turn only, then passes every later turn through untouched.

Mounts the mcptoon MCP gateway as one stdio server, so the agent discovers the tools of every MCP server you have configured through mcptoon's compressed view instead of full JSON schemas on each turn. Ships a doctor CLI that checks the mcptoon executable resolves and prints the exact command/args override when it does not.

One MCP tool instead of every schema you own — a lazy capability broker that cuts resident tool context by a measured 94.4%. Search, inspect, enable and call MCP servers and skills on demand.

Memory consolidation tuning for dsh-mneme (autoDream enabled, schema-max output budget, deepseek-chat route) plus the llm-deepseek reasoning-effort fix, an MCP bridge to the auditable seed-society agent runtime, and six yogacara seed skills.

Lets the AI insert streaming-generated UI into the conversation or a side panel, written in TSX — already one of the model's native languages, so there is no JSON schema to teach it. Rendered without flicker, state kept across frames with no hard remount, and a click in the card driving the next chat turn. Inline is where streaming matters most; the side Canvas is the more agentic shape. Cards get agentic capabilities of their own — run bash, curl, call the model, read and write files.

Per-profile settings overlay for DeepSeek Harness: global settings.yaml stays the baseline while each profile overrides any namespace through its own profiles/<name>/settings.patch.yml — object sections merge recursively, scalars and arrays replace wholesale, and !unset masks an inherited value. The overlay is transparent to existing plugins (they keep reading ctx.settings unchanged), writes land in the profile overlay only, and official schema validation, revision semantics, expectedRevision conflicts, watchers and events are untouched. Ships a settings command family (get/set/unset/mask/unmask/promote/demote/migrate/diff/layers) plus a Profile Settings section in the web Settings panel over a loopback RPC channel.

Per-agent on-demand tool discovery and progressive schema disclosure.

Read, audit and diff Protocol Buffer definitions without installing protoc: a zero-dependency .proto parser exposing six tools (status, outline, describe, diff, audit, next_number). diff classifies every change as breaking, risky or additive and names the wire-format consequence; audit catches what protoc accepts but a reviewer should not — duplicated or illegal field numbers, reserved-range collisions, unresolved types, and unreserved gaps below the high-water mark.

中文化 DSH 已知的系统提示词、MCP 指导与运行时提醒；按可见工具裁剪规则，保留工具 description、参数 schema 与动态值。纯 Host 插件，无 UI。

Model-facing codebase-memory CLI tools (codebase_list_projects/index_repository/index_status/search_graph/query_graph/trace_path/get_code_snippet/get_graph_schema/get_architecture/search_code/detect_changes/manage_adr/ingest_traces/delete_project) that ru

让 DSH 通过 CDP 驱动本机已开启调试的 Chromium 内核浏览器：常驻连接只授权一次，零新增工具 schema，零运行时依赖。Drive any already-running Chromium browser over CDP from DSH — one approval per connection, no extra tool schemas, no dependencies.

Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (pwsh, bash, write, edit) advertise the full sandbox_permissions enum, but DSH only accepts a level strictly wider than the one already in effect — a check its own source calls 'deliberately not a schema constraint'. A model that reflexively passes the argument therefore picks the level it is already at and the call dies before running with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "workspace-write" mode', costing some models a whole turn of retries. This plugin registers one tools/execute waterfall listener and, only on that documented rejection and only when the arguments really carried an escalation field, re-issues the identical call once without it. Safe by DSH's own documentation: the rejection precedes any execution ('nothing has run'), and the corrected call cannot match again, so the retry is loop-free. Reproduced and verified end to end — before: isError true, the command never ran; after: the command's real output, isError false, one tool/call and one tool/result. Zero dependencies.

Computer Use for macOS desktop applications: reads any app's accessibility tree as text with element indices, then clicks, types, pastes, scrolls, drags, selects text and sets values through it, plus screenshots read back as images. Driven by a persistent JavaScript REPL — the agent gets two tools (`js`, `js_reset`) and calls an `sky` API inside them, so state survives between calls and the tool schema stays fixed as capabilities grow. Accessibility trees come back as diffs after the first read; actions address elements by index and indices from a stale read are refused rather than misapplied; typing waits for keyboard focus and reads the field back; paste restores the clipboard. Requires macOS 14.4+, Accessibility permission (Screen Recording only for screenshots) and Node 20+; ships a prebuilt native module, so nothing compiles at install time.

Database connections and SQL for DeepSeek Harness: register data sources, browse and comment schemas, run AST-checked SQL with a per-source read-only toggle, and render bar, line and pie charts, from chat or the Settings page.

Read-only repository fact scanner kernel for DSH analysis plugins: deterministic probe / file index / modules / dependencies / entry points / symbols / graphs and git facts over a stable JSON schema (CLI + library + skill runbook).