Plugins

Verified-progress ledger: three tools record a claimed step as progress only after an independent subagent with a fresh context confirms it against the workspace. The declared scope is fingerprinted before and after each verification, so a verifier that changed anything has its verdict voided and the round cannot become progress.

Persistent Bots and group rooms inside DSH. Each Bot keeps its own model, permission preset, workspace and session across restarts; a Bot can also be backed by an installed local agent CLI (Codex CLI, Claude Code, ACP agents) using that CLI's own login and models. Unaddressed messages can be triaged by the room leader, the room accumulates a shared experience card, and every answer is a run in a durable ledger the sidebar panel replays. New Bots default to the full-access permission (any command, any file; the form asks you to confirm the risk), so choose read-only or workspace-write to confine one; Codex CLI and Claude Code Bots at full access run without their own sandbox or permission prompts.

A resident assistant for DeepSeek Harness that is deliberately not another chat box: one floating window plus one standing conversation, both independent of every other session. The heartbeat is held back by four gates — an authority grant, a daily turn budget, quiet hours and a pacing cooldown — and it keeps working across restarts through a lease it has to hold. Each wake is decided by a model that must answer SKIP or a short message, so silence is a decision rather than a failure. The window shows the standing conversation's real message flow, read from the host session store, or from the on-disk session log when the host does not publish that session, and it can send into that conversation directly. den carries the same reach as the person it stands in for, with one limit: read-only. It may read every session, this machine and work channels such as GitHub, but it does not write, send or publish, it never asks anyone for permission, and it never gates another session's tool calls. `npm run digest:github` turns GitHub notifications and your own open pull requests into three Chinese sections — waiting on you, waiting on your review, and yours — with reply drafts that are explicitly marked as unsent.

Daily brief for DeepSeek Harness. Every day at a fixed hour it ranks the plugin market by real install counts and stars, cross-checks it against your own agent memory and working conventions, and proposes two kinds of item: concrete deltas on the plugins people actually use (original does A, the proposal does B) and directions nobody has built yet. The popularity numbers come from the catalog the market itself publishes and are quoted into the prompt rather than guessed; an entry the market has not measured is shown as unmeasured, never as zero. Approving an item opens a new session named after it and hands that session a fixed delivery contract — implement independently, never fork, test green before publishing. Rejected sources are remembered so they stop coming back.

Daily and weekly task manager: startup popup reminder, a marquee strip above the composer, one-click circle completion, editable task cards, and a Sunday AI weekly summary, plus a sidebar DeepSeek API usage widget with balance card, today/cumulative tokens and cost, per-model breakdown and a 7-day chart. Persists as JSON under $DSH_HOME.

Answers a hard question with a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled dependency-free `am` CLI builds the layout, CSS and diagram coordinates. Vendors the upstream answer-me-with-html skill verbatim as a skill-only DSH bundle with no Host code.

Skill-creation console for the Web UI: fetches the official creator skills, hands the requirements to the Huawei Cloud, generic, or REST API creator, then scores the generated skill against a 10-point rubric and returns the itemised deductions to the creator until it reaches 8.5/10.

A mandatory 7-step plan on every request, each step with a binary acceptance criterion, executed through worker subagents and validated by independent memoryless verifier subagents that report PASS or FAIL with evidence.

Write and read Markdown notes: switch between reading, editing and side-by-side preview, with an outline, three preview themes, math and Mermaid, nested folders, and autosave to local .md files.

Publishes HTML pages and Markdown documents written by the agent to GitHub Pages as shareable links, with tools to update them in place, list, read back, and delete them; adds an Artifacts sidebar panel and a bundled page-design skill.

Generates release material from what a local repository can actually support: a hero image, a feature grid and bilingual copy rendered as SVG and HTML from `README.md`, `package.json` and optional screenshots. Facts are quoted from those files — name, version, license, summary, features, install snippet — and a field that is missing is left unrendered rather than filled with placeholder text. Every feature carries a source citation such as `README.md#L42`, and a claim the repository cannot substantiate is linted out before anything is written, with the reasoning left in `lint-report.json`. `manifest.json` records a sha256 for each input and output, and `--now` or `SOURCE_DATE_EPOCH` makes a run byte-identical. Also ships a GUI panel that regenerates from inside a session.

Adds an Omni-modal settings section to DeepSeek Harness that points the harness at any OpenAI-compatible image and video endpoint: switchable config profiles with separate endpoint, API key, model, path and size for each side, free-form extra request parameters, a connectivity test that does not spend generation quota, and three model-visible tools — generate_image, generate_video and check_video — with async video tasks that survive restarts.

Pixel-level screenshot diff for visual regression. Two local PNGs in; a machine-readable first line (`PIXEL_CHANGED=true|false`, greppable as an assertion), then the difference ratio, per-region bounding boxes, maximum channel delta and mean absolute error, plus a self-contained HTML comparison page. An ignore-region list with absolute or fractional coordinates excludes clocks, cursors and other per-render noise. It deliberately does no content recognition: it answers only "did this change", which is the part that can be made deterministic. Entirely local — no model call, no network, no upload.

Keyless web powers for any MCP client: web_search, JS-rendered web_extract over dual CDP Chrome with proxy failover, and 7 real-browser page_* tools in an isolated context.

OpenAI-compatible web search provider for the built-in web_search tool: one baseURL/apiKey/model config powers Qwen Token Plan, OpenAI and any Responses API gateway.

Annotate pages inside the existing Harness Browser: click or drag to select, comment or ask, then send marked screenshots or DOM location details to the current session. While enabled it replaces the official Browser, Chat and Layout providers; targets Harness 0.2.1-alpha.2.

Panel for MCP servers registered by @deepseek-ai/dsh-mcp-client: toggle each server on or off with live effect, see the registered tool count and estimated context-token cost of each server, and persist the choice to the home cordis.patch.yml with a timestamped backup before every write. The panel itself can sit either as a page inside Settings or as an icon row in the left sidebar, one seat at a time, with the switcher on the plugin page in Settings. Maintained fork of dsh-mcp-toggle.

Bridge between DSH and the local WorkBuddy desktop app, in four parts: read, search and append WorkBuddy memory, skills, plans and daily logs; run tasks through the local CodeBuddy CLI with four permission profiles; drive the running WorkBuddy window over CDP (open a conversation, read its replies as sanitized rich HTML, type and send, switch the account-billed model, relaunch it with a debug port when it is missing); and a sidebar panel that puts that conversation surface inside DSH. 25 tools and 15 HTTP routes in one plugin.

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.

E-commerce plugin for DeepSeek Harness — product search, comparison and checkout across Taobao/JD/Pinduoduo, via the yuantoutao Streamable HTTP MCP server.

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.

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.

Generate images and videos directly in chat and deliver them to the conversation: generate_image / generate_video / send_media tools, a built-in Agnes free tier plus any OpenAI-compatible backend, background jobs that auto-push finished media, and inline gallery and video cards with download, lightbox, and native open.