tt-a1i/archify#integrations/deepseek-harness
Generate validated, self-contained interactive architecture, workflow, sequence, data-flow, and lifecycle diagrams from repositories or system descriptions.
Install
via npm
Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.
The desktop app keeps its own profile, desktop, and only the dsh command it ships may change it — the npm-installed dsh refuses that profile. Install the command from the app menu (Manage dsh Command…), open Desktop once, quit it fully, run the line below, then reopen Desktop.
via npm
Resolves a published tarball rather than cloning the repository.
Our install check ran in a web profile on npm's dsh, not in the desktop app.
What happened when we ran it
Installed cleanly when we ran it
Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 6d agoon DeepSeek Harness 0.2.1-rc.5.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
Security
No build script was blocked in our run.
Source: our sandbox install on DeepSeek Harness 0.2.1-rc.5, 6d ago.
package.json declares no preinstall, install or postinstall script.
Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.
shell commands (bash, exec, spawn …)
Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.
Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.
What it is — Archify as a DeepSeek Harness plugin: it turns a repository or a system description into a browsable diagram.
Who it is for — You are on a DeepSeek model in Harness, inherited a multi-service repo with no architecture notes, and you need a map of request and data paths a teammate can open. If alignment in your loop is PR plus CI and people read diffs, skip it.
Watch out — A clean profile accepted the install, and DeepSeek Harness registered the plugin. Drawing shells out on the machine, so the agent gains command-line reach while it works. The sandbox did not hit an install or registration failure.
The verdict — Leave it off the profile that only ships patches; load it on a separate one reserved for walkthroughs.
Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.
deepseek-harness is a DeepSeek Harness plugin that turns repository context or a written system description into interactive diagrams.
The upstream Archify workflow is driven through an agent prompt. The agent can be asked to read a repository or use a description such as a browser-to-API request with Redis, PostgreSQL and a cache-miss path. Archify then generates a self-contained interactive HTML diagram. The README describes source links, path tracing, follow-up changes such as adding authentication or highlighting a route, and theme changes. It does not name a DeepSeek Harness hook, configuration key, output directory, or plugin-specific command.
DeepSeek Harness provides this plugin for developers who need source-backed or explanatory visuals for architecture, workflows, sequences, data flows, or lifecycles. A repository is optional, so it can also be used for an early design or system explanation. The terminal surface matters: the repository-reading workflow can expose project contents to the agent, within the permissions available to DeepSeek Harness. Choose another tool when the required output is a static image, a documented native DeepSeek Harness diagram format, or a workflow whose integration details must be configured explicitly; the README documents interactive HTML and agent prompts, not those alternatives or DSH-specific settings.
The README presents Archify as an agent-directed workflow rather than a standalone diagram editor. An agent can receive a natural-language system description or be asked to inspect a repository. The resulting artefact is a self-contained interactive HTML document. The documented examples cover architecture and web-request flows, while the project summary also names workflow, sequence, data-flow and lifecycle diagrams.
Generated diagrams can be explored through source links and path tracing. The README also shows iterative requests after generation, including adding authentication, highlighting the cache-miss path and switching to a light theme. A repository is not required when the diagram can be described directly.
DeepSeek Harness exposes this capability through the deepseek-harness plugin. The upstream README explicitly lists compatibility with Cursor, Claude Code, Codex CLI and OpenCode, and documents the npx skills add tt-a1i/archify -g skill-installation workflow for those environments. It does not document a DeepSeek Harness hook, a plugin configuration file, configuration keys, environment variables, or an output path.
The README documents interactive HTML as the output and does not specify a static-image export, a native DeepSeek Harness diagram format, or repository-language restrictions. Repository access depends on the agent being able to read the relevant project in its environment. Because this plugin has a terminal surface, repository contents may be reached during that workflow through the permissions granted to DeepSeek Harness.
Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub
Same category
dream-num
Give DeepSeek Harness a real office environment. Univer Office Plugin brings spreadsheets, docs, slides, canvases, relational tables, and more into one runtime — with connected data, validation, versioned changes, and isolated worktrees for multi-agent collaboration.
Installed cleanly when we ran it
A workspace-based Studio for source-grounded reports, slides, tables, mind maps, quizzes, flashcards, audio and video, using DSH models and shared artifact services. Office generation requires Python 3.12+ with its dependencies and DSH_OFFICE_PYTHON configured; media rendering requires Chromium, and local ASR additionally requires whisper.cpp and a model.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
PerryLink
Deterministic industry research reports for DeepSeek Harness — company and industry research flows produce structured, verifiable reports from staged evidence.
Installed cleanly when we ran it
Roland0511
WYSIWYG Markdown editor in the DSH right sidebar, built on MarkText's muya engine: open a .md file, edit it as a rendered document, and save back through ctx.fs with a version guard.
Installed cleanly when we ran it
joeseesun
Browse UI design references and interaction examples, take design quizzes, and export learning notes as Markdown.
Installed cleanly when we ran it
PolinniZhong
Puts the Markdown documents, source files, images and video that already exist anywhere in the session workspace into the DSH sidebar, ranked by relevance to the current conversation. The default lexical mode matches your recent messages against title, summary and body locally with IDF weighting (BM25) — no model calls, no network, nothing leaves the machine. The list comes from scanning the workspace rather than from a recent-files list, so restarting DSH or opening a new session does not empty it. Results are organised into a three-tier reading order (primary / supporting / related) with a verifiable reason on every row — which field matched, which document cites this one — and one click opens an in-place preview: Markdown as rendered text, relative-path images actually drawn, source code with the host's own syntax highlighting, video streamed over HTTP Range. The same Context Pack is exposed to the agent as a knit_docs tool. Later versions added read evidence and lifecycle tracking (attribution is frozen at the moment of reading), pin / exclude (exclusion applies before retrieval, and is undoable), relation evidence (references / imports / tests, with line numbers) and an incremental index reused across restarts. Since v0.23 there is also an optional hybrid mode: it is off by default and only runs once you configure an Ollama or OpenAI-compatible embedding provider yourself. When it runs, what leaves the machine is your query text plus each candidate file's title and summary — a Markdown summary is an excerpt of the body's first paragraph (at most 60 characters), a code file's summary is its workspace-relative directory, and an image or video contributes its file name; full bodies and absolute paths are not sent, and a loopback provider keeps everything on this machine. Since v0.24 it also associates uncommitted changes: a read-only git status (fixed argv, no shell, whitelisted child-process environment) combined with the same reference / import / test / mention evidence shows which files a change is likely to drag along, and it is off by default. The benefit of semantic retrieval still awaits a real-provider run, so no recall improvement is claimed.
Installed cleanly when we ran it
