One-Line Positioning

dsh-crew is a plugin for the DeepSeek Harness (DSH) platform that enables Claude Code or Codex to dispatch tasks to DSH's DeepSeek agents while preserving the native subtask panel; it also adds image description and generation capabilities to the text-only DeepSeek model.

Core Capabilities

• Dispatch tasks to DSH agents at flash / pro tiers, with real-time progress, current tool, and token usage displayed in Claude Code / Codex's native subtask panel
• Support synchronous blocking calls (dsh_run_worker) and asynchronous fan-out calls (dsh_spawn_worker), with the latter usable with status query and polling interfaces
• When DSH Web instance is running (hub mode), dispatched tasks become DSH top-level sessions, viewable by working directory in the Web UI; otherwise automatically falls back to standalone runtime (available for CI, headless environments)
• Provide describe_image and generate_image tools for text-only DeepSeek models, usable with local CLIs like Claude / Codex / Grok / Antigravity, or any OpenAI-compatible endpoint/local command
• One-click installation to Claude Code and Codex: register local market, write MCP tool whitelist, integrate claude-hud status bar segment, backup all settings files before modifying
• Configurable tier policy (force flash-only or pro-only) and failure escalation (auto-retry with pro when flash fails), enforced at tool layer rather than by verbal agreement

Technical Implementation

• Language: TypeScript / JavaScript (ESM)
• Key Dependencies: @modelcontextprotocol/sdk, MCP stdio protocol; DSH SDK client (lazy-loaded on-demand for standalone mode only); zod (parameter validation)
• Architecture Pattern: Provides two forms simultaneously — MCP stdio server (src/server.mjs) as a client-side shim for Claude Code / Codex; DSH Cordis host plugin (src/hub/index.mjs, mounted to DSH runtime via cordis.patch.yml) as the server-side; the two communicate via local loopback HTTP interface (/_dsh/dsh-crew/jobs) and auto-switch
• Entry Points: src/server.mjs (MCP entry), src/hub/index.mjs (DSH host plugin entry), outer package.json#dsh.bundle + cordis.patch.yml describe how to inject DSH Web profile

Use Cases

Developers who have subscribed to Claude Pro or regularly use Claude Code / Codex, and want Claude to actually "do the work" instead of just acting as a dispatcher: let Claude delegate independently solvable subtasks to DeepSeek agents while continuing to use their familiar Claude desktop workflow; and use DeepSeek for coding tasks in CI environments without a DSH Web interface. In developers' daily work, DSH models only support text; with the plugin, they can use locally logged-in Claude / Codex and other CLIs to help it "see images" and "draw".

Prerequisites & Compatibility

Installation

dsh plugin --profile web add github:ZSeven-W/dsh-crew

Configuration Options

Configure via DSH Web settings page DSH Crew panel, or directly edit ~/.config/dsh-crew/config.json.

FAQ

Q: What additional configuration is needed after installation?

A: If DSH Web is running (hub mode), it already has DeepSeek credentials, and the plugin works directly. Only in pure standalone mode without a DSH instance do you need to write DEEPSEEK_API_KEY to ~/.config/dsh-crew/.env.

Q: DeepSeek is a text-only model; how about images and generation?

A: The plugin includes describe_image and generate_image tools, using locally logged-in subscription CLIs (Claude, Codex, Grok, Antigravity) or any OpenAI-compatible API/local command to handle image description and generation; images pasted into the session are automatically converted to text before being sent to the model.

Q: How to choose between dsh_run_worker and dsh_spawn_worker?

A: dsh_run_worker is a blocking call that returns with results; dsh_spawn_worker immediately returns a task ID, suitable for parallel fan-out, with results tracked via dsh_worker_status / dsh_worker_result.

Q: What's the difference between flash and pro tiers?

A: flash is fast and cheap, suitable for mechanical tasks; pro has stronger reasoning, suitable for complex tasks. You can use tier_policy to pin all dispatches to a single tier, or enable automatic retry with pro for failed flash tasks.

Q: How to uninstall?

A: Click the uninstall button in the DSH settings page DSH Crew section, or run node src/install/cli.mjs uninstall from command line; it will clean up Claude Code / Codex registration and HUD segments, while retaining backups of settings.json.

Q: What operating system is needed?

A: Only uses Node built-in modules and subprocesses; any desktop system that can run Node works, cross-platform on macOS / Linux / Windows.

Learning Curve

Beginner — After the plugin is attached to the DSH profile, you can dispatch via natural language like "dispatch X to ds-flash" directly in Claude Code / Codex; enter the DSH settings page to adjust when image description or preset changes are needed.

Known Issues & Limitations

• Client subtask shell is forwarded through Claude's own small model (haiku, etc.), consuming hundreds to thousands of additional Anthropic tokens per dispatch (from README original): either accept this cost, or work around it (the README mentions a router experimental route, but Codex side requires API key while subscription OAuth is blocked by upstream 403, not officially supported)
• Generated images are single-layer bitmaps; layer editing still depends on external tools like OpenPencil
• Codex roles must set default_tools_approval_mode = "approve", otherwise tool calls are automatically cancelled
• Client process and host process communicate via local loopback HTTP; polling requests waiting more than a few tens of seconds are cut off by Node undici's 300-second header timeout, so the plugin actively splits into ≤ 60-second slices during waiting (src/hub-client.mjs:31-41), but extremely long tasks still require active polling via dsh_worker_result(wait_seconds)
• When imagegen_provider selects Codex/Grok/Antigravity CLIs, the corresponding CLI must be locally logged in; the plugin won't bypass their authentication

DSH Crew

A DeepSeek Harness plugin: dispatch work to DSH agents from Claude Code / Codex, without giving up the host's native subagent UI.
_{Native Progress UI • Tier Policy & Escalation • In-Host DSH Sessions • Vision & Image Generation • One-Click Install}

_{npm: @zseven-w/dsh-crew · Current plugin release: 0.1.0-rc.3 · Tested with DSH 0.1.0-rc.6}

English · 简体中文 · 繁體中文 · 日本語 · 한국어 · Français · Español · Deutsch · Português · Русский · हिन्दी · Türkçe · ไทย · Tiếng Việt · Bahasa Indonesia

_{The DSH Crew settings page — host integrations, dispatch policy, execution and the multimodal bridge}

Why DSH Crew

DSH Crew is a plugin for DeepSeek Harness (DSH) — an open-source agent harness. It makes DSH agents dispatchable from Claude Code and Codex: the orchestrator keeps its own model, the work runs on a real DSH agent with that harness's tools, sandbox, presets and session history, and the host still shows it as a native subagent with live progress.

What runs the work is a DSH agent, not a bare model call. Tiers (flash / pro) select how much capability that agent gets from the harness's configured roster — DeepSeek V4 Flash and V4 Pro today — so a change of model in DSH needs no change here.

How it works

Claude Code / Codex (orchestrator, keeps its own model)
  └─ ds-flash / ds-pro  ← native subagent shell (progress shows in the host's task UI)
       └─ MCP: dsh_run_worker(tier, effort, cwd)
            ├─ hub reachable → session inside DSH (visible in the Web UI, grouped by cwd)
            └─ otherwise     → dsh-jsonrpc-agent runtime (worker.cordis.yml)
                 └─ DeepSeek V4 Flash / Pro (DSH SDK, event stream → progress and token stats)

One run, two views

Dispatch fans out. Below, eighteen workers translate this README in parallel: the host counts them as its own subagents, while the harness runs them as real sessions.

_{Claude Code sees dsh-crew workers as native subagents, with a statusline segment tracking running tiers, elapsed time and tokens.}

_{The DSH Crew panel sees the same run from the harness side: which host dispatched each job, its tier and effort, live progress and token usage.}

Install

Install into a DSH profile from npm:

dsh plugin --profile web add @zseven-w/dsh-crew@latest
dsh web

Or, for local development straight from the source tree:

dsh plugin --profile web add link:/path/to/dsh-crew
dsh web

The link: protocol symlinks the profile dependency to this repository, so rebuilds are visible immediately.

Configure DeepSeek credentials (standalone only)

In hub mode — the installation above — workers run inside the DSH instance and use the DeepSeek credentials it is already configured with. Nothing else to set up.

Only the standalone fallback needs a key of its own: dispatching from Claude Code / Codex with no DSH instance running launches a worker runtime as a separate process. Obtain an API key from platform.deepseek.com and write it to ~/.config/dsh-crew/.env:

DEEPSEEK_API_KEY=sk-...

Verify

node scripts/smoke.mjs

The smoke test dispatches one cheap job through whichever path is available — the hub when a DSH instance is running, standalone otherwise — and prints which one it used. Within about ten seconds you should see smoke test passed — configuration OK. On failure the reason is printed, scoped to the path that was tested.

Then open Settings → DSH Crew and install the Claude Code / Codex integrations with one click.

Background and terminology

• DSH (DeepSeek Harness): DeepSeek's open-source agent harness, a code agent in Web UI form, similar to Claude Code but driving DeepSeek models.
• MCP (Model Context Protocol): Anthropic's AI tool integration protocol, enables LLMs to safely call external tools and data sources.
• Cordis bundle: DSH's plugin format; this project can run standalone as an MCP service or install into DSH Web as hub mode.
• tier: capability tier — which slot of DSH's configured model roster a worker gets. flash is fast and cheap (simple tasks), pro reasons harder (complex problems). Today they map to DeepSeek V4 Flash and V4 Pro; swap models in DSH and nothing changes here.
• worker: the DSH agent doing the work — a full session with its own tools, sandbox and preset, not a bare model call.
• effort: reasoning strength, off = no reasoning, high = high reasoning investment, max = maximum reasoning investment.

Claude Code

Installation

One-click installation (choose one):

• DSH settings page (when hub mode is installed): Settings → DSH Crew → "Install to Claude Code"
• Command line: node src/install/cli.mjs all

Both do the same thing: register local marketplace (parent directory dsh-plugins/ as marketplace root) + claude plugin install + MCP tool permission allowlist + claude-hud worker status segment config (auto-backup settings.json before changes, idempotent). Restart the session after installation for changes to take effect.

Usage

• Directly in conversation, say "dispatch X to ds-flash" or "dispatch X to ds-pro", and subagent executes the task
• Dispatch count and real-time progress shown in Claude Code task UI
• HUD status line segment: ⚙dsh 1▶pro 2m14s 21.7k/606 ✓3 (current tier / elapsed time / token usage / completion count)
  • For local development, statusline/statusline.sh or statusline/worker-segment.sh can be independently integrated
• Long-running tasks: CC has timeout limits on MCP calls (MCP_TOOL_TIMEOUT adjustable), long tasks can have orchestrator use dsh_spawn_worker + dsh_worker_result(wait_seconds) polling
• Local development and debugging: claude --plugin-dir /path/to/dsh-crew to temporarily load

Session commands

These override the global defaults for the current session only, and are enforced at the tool layer rather than by prompting:

Codex

Installation

Recommended to use the installer (auto-renders paths for this machine, copies /dsh-config, /dsh-status commands):

node src/install/cli.mjs codex

Or manually copy (requires manual path modification after copying):

cp codex/agents/*.toml ~/.codex/agents/    # global or project-level .codex/agents/

Role files come pre-configured with:

• MCP server mounting configuration
• default_tools_approval_mode = "approve" (required, otherwise tool calls are auto-cancelled in exec mode)
• tool_timeout_sec = 3600

Note: When manually copying, absolute paths in the args field must be updated to match actual installation location; the installer handles this automatically.

Usage

• In interactive TUI, select "spawn ds-pro to ..." to dispatch tasks; Active/Done panels show progress
• codex exec mode can also directly call dsh_run_worker

Session commands

The same two prompts are installed for Codex:

MCP tools

Progress is simultaneously mirrored to ~/.config/dsh-crew/status.d/ (one shard file per writer, can be read by statusline / external monitoring).

Multimodal: vision and image generation

DeepSeek is a text-only model and does not support image input or generation. This plugin sources these capabilities externally through MCP tools:

Session image pasting: In DSH, switch model to DeepSeek (vision) ◉ to directly paste images. Images remain in session and display normally; the plugin appends transcribed text after them and strips images before sending—you see the image, the model reads the text.

Configuration

In DSH settings page → DSH Crew → Multimodal (or directly edit ~/.config/dsh-crew/config.json):

Vision provider (image viewing):

• claude-code (default, uses haiku, inexpensive)
• codex (uses GPT, can specify specific model)
• grok (uses Grok)
• agy (Antigravity)
• custom (OpenAI-compatible API or local command)
• off (disabled)

Image generation provider (image generation):

• codex ($imagegen, gpt-image-2)
• agy (Nano Banana)
• grok (Imagine)
• custom (OpenAI-compatible API or local command)
• off (disabled)

Custom provider

Two integration methods:

API: Any OpenAI-compatible endpoint

• Fill Base URL, API Key, model list
• Vision uses /chat/completions with inline base64 images
• Image generation uses /images/generations
• Must specify "image generation model" to have generation capability, otherwise provider only appears in vision selection

CLI: Local command template, placeholders substituted with safe references

• Vision: {image} {question} {model} → stdout as answer
• Image generation: {prompt} {output} {size} → command must write file to {output}
• Fill at least one command; whichever is filled determines capability

Connectivity test: Each custom provider has a test button

• API: Check endpoint reachability, auth, send real vision request to verify
• CLI: Check executable file, run real command to verify
• Image generation: Validate config only, no actual image output

Borrowed subscription CLIs (claude / codex / grok / agy) require you to be logged in locally; the plugin won't bypass their permissions for you.

Hub mode

This package is also a valid DSH bundle (dsh.bundle + cordis.patch.yml). After installing into DSH Web profile with dsh plugin add dsh-crew:

• Worker sessions become first-class citizens: run as first-class sessions in DSH host (agents.create + per-session model/effort waterfall + default preset), appear in Web UI session list, can be opened anytime to view complete execution
• Organize by working directory: manage worker sessions by cwd in Web UI
• Loopback API:
  • POST/GET /_dsh/dsh-crew/jobs: spawn tasks, list, long-poll results, cancel
  • GET /_dsh/dsh-crew/ping: health check (MCP shim uses this to detect if hub is running)
  • POST /_dsh/dsh-crew/install: one-click install Claude Code / Codex integration (backend of src/install/)
• Auto-detection: CC/Codex's MCP shim auto-detects hub (DSH_CREW_HUB env var, default http://127.0.0.1:3080)
  • DSH Web running → jobs enter hub mode (mode: "hub")
  • Not running → fall back to standalone runtime

Solution selection and limitations

Regular subscribers → shell subagent approach (recommended)

• Current state: Claude Code subagent shell uses haiku as intermediary; each dispatch adds hundreds to thousands of tokens
• Trade-off: Use small amount of Anthropic token in exchange for native task UI, real-time progress display, no extra configuration
• Recommendation: If you already subscribe to Claude Pro or use Claude Code, use this approach—convenient and transparent

Pay-as-you-go / CI environments → direct router approach

• Current state: Claude Code subagent frontmatter doesn't support direct third-party model connection; this repo's router experiment in scratchpad requires API-key credentials for Claude Code, but subscription OAuth is blocked upstream by Anthropic with 403
• Recommendation:
  • If using API-key credentials (not OAuth) and want to save Anthropic tokens, can run local router for direct DeepSeek connection
  • CI environments typically also use API keys; this approach is more economical (all DeepSeek tokens)
  • Requires self-testing of router integration (not officially supported)

Running DSH Web → hub mode auto-enabled

• Current state: If dsh plugin add dsh-crew installed into DSH Web profile, jobs run as first-class sessions in host, appear in Web UI session list
• Recommendation: During local development iteration, recommend enabling hub mode; worker progress can be fully observed in Web UI; for cross-machine collaboration or environments without Web UI, use Claude Code / Codex shell approach

Known items

• Codex role can theoretically try model_provider pointing directly to DeepSeek (unverified); this bridge doesn't depend on it
• Image generation output is flat bitmap; layer editing requires OpenPencil
• Runtime dependencies: Only @modelcontextprotocol/sdk and zod; @deepseek-ai/* are host runtime, provided by the DSH host (a plain npm install never pulls them)
• Codex must configure: default_tools_approval_mode = "approve", otherwise tool calls are auto-cancelled

Develop

pnpm install
node_modules/.bin/tsdown src/client/index.tsx --format cjs --platform browser \
  --target es2022 --tsconfig tsconfig.client.json --out-dir .client-build --clean
node scripts/build-client.mjs   # wraps the bundle for the DSH module loader
node scripts/smoke.mjs          # dispatches one real flash task end to end

Runtime dependencies are only @modelcontextprotocol/sdk and zod; every @deepseek-ai/* package is host runtime provided by the DSH host (documented in the package's dshHostRuntime field, not in peerDependencies, so a plain npm install never pulls them), which keeps the plugin inside the host's single module realm.

Ecosystem

• DSH iOS — a live iOS Simulator and a USB-connected iPhone, inside the conversation
• DSH Noema — long-term memory for DSH
• DSH OpenPencil — inspect and edit .op design documents inside a conversation

License

MIT