Plugins

Code retrieval engine exposed as an MCP server: four tools (code_search, code_outline, code_index, index_status) over a SQLite FTS5 index with BM25 ranking, CJK bigram indexing, declaration-aware tree-sitter chunking, incremental reindexing, and a three-layer secret filter. The bigram index matches Chinese-language queries against English code, and the default path needs no vector store or embedding model. Requires a local Python 3.10-3.12 engine installed by scripts/install.sh, and CODERAG_ROOT set in the profile patch.

CCReach capability-search provider for DeepSeek Harness, letting agents discover data sources, tools, APIs, MCP servers, skills and workflows.

MCP server manager for DSH: nine mcp_manager_* tools, a CLI and a web panel that list, validate, probe, add, edit, enable/disable and remove servers in ~/.dsh/cordis.patch.yml, search and install servers from the official MCP Registry, and locate or rotate stored credentials.

Bidirectional bridge between Hermes Agent and DeepSeek Harness: dispatch_task with UI-visible sessions in the DSH sidebar, session mirroring, and 10 DSH-to-Hermes tools.

Turn-level file undo for tool writes and edits: each file is snapshotted before the write lands, and the model (an undo tool), the human (a /undo command) or a button in the assistant message action row can roll back every file a turn changed. Snapshots are written in-process rather than by shelling out, so it needs no extra sandbox permission in sessions confined to workspace-write.

AList v3 file management: browse, search, upload (streamed and multipart), offline downloads, archive listing, task polling and control, plus admin tools for storages, users, roles, meta rules, settings, search index, shares and labels - 75 tools in total; every write goes through the approval flow and passwords are never read back.

Zotero library in a read-only sidebar panel: browse collections, search items, read metadata and full text, and insert a single citation, a selected excerpt, or a whole collection into the conversation draft. A self-hosted bridge connects to the local Zotero integration MCP and registers its tools to the model as mcp__zotero__*, each one individually toggleable.

Reads Claude Code and Codex plugin configurations to discover and preflight MCP servers and slash commands, with opt-in registration in DeepSeek Harness.

Agent mode picker for DSH: pick an external Agent CLI (Claude Code, Codex, Qwen Code, Gemini CLI, Aider, Goose, Hermes…) as the session's default executor from a control next to the input box, instead of editing configuration files. The agent roster is data-driven, and installed CLIs are discovered automatically from PATH, the managed CLI directory and a drop-in convention directory. Agents that are installed but still missing credentials or a required background service are shown as "needs setup" rather than silently hidden.

Merged web search provider: every web_search fans out to serper.dev (Google SERP with answer box) and DeepSeek native search in parallel, unions the URL-deduped sources, and degrades to whichever backend answers. Plugins-page settings card with credentials-domain API key and a native-merge toggle.

E-commerce plugin for DeepSeek Harness — product search, comparison and checkout across Taobao/JD/Pinduoduo (50k+ curated SKUs), via the yuantoutao Streamable HTTP MCP server.

Manage Postman cloud collections from dsh with 9 tools — list, browse, add one or many requests, edit and delete them, and export or overwrite a whole collection.

Full upstream REA 6.4.0 integration over the official DSH MCP bridge: all 170 tools, the version-matched reverse-engineering skill, and the six original MCP prompts with argument completions reachable from the composer / menu, all sharing one REA process and complete structured Evidence. External analysis engines are bring-your-own.

Bridge to the UnrealAgentLink editor plugin: the Unreal Engine editor dials this WebSocket bridge on 127.0.0.1:17860 and the agent drives it through 12 tools covering all 170 cataloged commands (actors, levels, blueprints, materials, PCG, screenshots, logs, undo).

Folder time machine for DeepSeek Harness: snapshot any folder, browse its timeline, roll back with one click — Git-like history without needing Git, for folders that never had a repo (game saves, app config dirs, loose documents). Snapshots are content-addressed and deduplicated, and unchanged files are not re-hashed. Automatic snapshots come in two modes: realtime (fs.watch — one version ~8s after the last change, so a save-all or a build counts once) and timed (checks every N minutes, stores only when something actually changed; identical content never adds an empty version). Empty folders are recorded and recreated on restore. Every restore takes a safety snapshot first, so a rollback is itself undoable, and exact-mode cleanup only removes files and empty folders — a non-empty folder is never deleted. Ships a folder_timemachine model tool (status/history/diff need no approval; writes ask first) plus a floating panel with the timeline, one-click restore and mode switching. Pure JS, zero runtime dependencies, 110 tests included.

Imports the MCP servers Codex and Claude Code already declare as dsh mcp-client tools, links the skills of 22 known agent skill directories into ~/.dsh/skills as symlinks instead of copying them, and adds a Settings page that lists what was mounted, toggles each skill, and changes the source on a name conflict.

Chooses which skills and MCP servers each workspace may use, from a "Skills & MCP" item in the workspace row's "..." menu; unchecked skills leave the session catalog, the `skill` tool and `/name`, and unchecked servers have their `mcp__<server>__*` tools denied for that workspace's sessions, running ones included from the next turn.

Bridges the AtomCode terminal AI coding assistant already signed in on this machine into DeepSeek Harness as two side tools: atomcode_ask (a side-conversation relay with per-working-directory session continuity) and atomcode_review (a one-shot, bounded code review with structured findings). atomcode_ask needs no API key and takes over no model — it reuses the AtomCode session already signed in on this machine. atomcode_review additionally requires a direct provider (standard API with an explicit api_key) configured in DSH; without one it refuses before calling. The settings card adds a read-only CodingPlan quota read-out, and each tool names its own model default.

A shareable delivery receipt for a project hand-off. The `ship_receipt` tool measures what it can and records what it was told, then sorts every line into three zones: verified (evidence this run produced and that reproduces elsewhere — a command that actually ran with its exit code, a file hash for a file that is under version control, a scan that found files, a git ref present in the recorded remote), local-only (true on this machine alone — uncommitted changes, unpushed commits, an artifact no one else can see), and unverified (no evidence, including every sentence a human typed). A claim with no evidence keeps its label and leaves the body blank rather than printing the claim; declares the commit and branch, artifact byte sizes and sha256 with PNG dimensions, and the three pre-push checks.

A delivery receipt panel for a project hand-off. One trigger collects the branch and commit, the test and build results, screenshot dimensions with sha256, and the secret-scan verdict, then assigns every line to one of three zones by evidence alone — verified, local-only, or unverified. A claim in the unverified zone keeps its label and prints an explicitly empty slot instead of the claim itself, because a confidently worded sentence with nothing behind it is the exact thing the receipt exists to catch. Test failures and secret-scan hits are still evidence, so they land in the verified zone with a red tone rather than being quietly dropped.

Import the copied connection information from the new API site with a single click.

Balance dashboard, allowing the addition of multiple pay-as-you-go/Token plans, while simultaneously checking balances.

Literature search tools for DeepSeek Harness: four model-facing tools — paper_search, paper_get, paper_citations and book_search — over OpenAlex, arXiv, Crossref, Semantic Scholar and PubMed, with open-access PDF resolution through Unpaywall.

Normalizes every tool schema before it reaches the model, rewriting it into the strict OpenAPI 3.0 subset that Gemini function declarations accept — a type on every node, items on every array, no empty enum entry, $ref inlined — so a single offending MCP or built-in tool no longer fails the whole request with HTTP 400.