dsh-setup

An installation and management guide for DeepSeek Harness, a web-based agent workspace where features are provided as plugins. It covers persistent installation, a Chrome app launcher, and GNOME desktop integration.

In plain words
What is it for?
Use it to install DSH with pnpm, manage its user service, launch it in Chrome app mode, and integrate it with GNOME.
Why use it?
It avoids unreliable temporary installs and gives the harness a repeatable way to start, stop, update, and manage its data.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/rhtevan/agentfs/dsh-setup
Any agent
npx skills add rhtevan/agentfs --skill dsh-setup
Clone the repo
git clone --depth 1 https://github.com/rhtevan/agentfs

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,913 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.01913
Opus 5 $0.00015 $0.00957
Sonnet 5 $0.00006 $0.00383
Haiku 4.5 $0.00003 $0.00191

Measured 2d ago against content hash fbd2b61c159f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dsh-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/install-desktop.sh, scripts/install.sh, scripts/teardown.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/dsh-setup/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DSH Setup — Install, Launch, and Manage DeepSeek Harness

Install and manage DeepSeek Harness (dsh) as a locally-installed agent harness with a dedicated Chrome app-mode launcher and GNOME .desktop integration. DSH is a WebUI-based agent harness where everything is a plugin, powered by Cordis.

This skill uses pnpm for package management (npm cannot handle DSH's 62+ direct dependencies — it hangs indefinitely consuming 3+ GB RAM). The install is persistent (not ephemeral npx), so launches are instant (~3 seconds) and updates are explicit.

Prerequisites

  • Node.js ≥ 22.19.0 or ≥ 24.0.0 (node --version)
  • Google Chrome installed (/usr/bin/google-chrome)
  • Internet access for initial install and updates

Architecture

Component Path Purpose
pnpm ~/.local/share/pnpm/ Package manager (installed once)
DSH install ~/.local/share/dsh/ pnpm-managed DSH + node_modules (~250 MB)
DSH home ~/.dsh/ DSH user data, settings, credentials, sessions
Systemd service ~/.config/systemd/user/dsh.service Backend lifecycle (start/stop/status/logs)
Chrome profile ~/.local/share/dsh-chrome-profile/ Separate Chrome profile for security isolation
Launcher ~/.local/bin/dsh-launcher Starts service → Chrome app-mode (maximized) → waits for Chrome exit → stops service
Desktop file ~/.local/share/applications/dsh.desktop GNOME app launcher entry
Icon ~/.local/share/icons/hicolor/*/apps/dsh.png App icon (48, 128, 256, 1024px)

DSH stores its config in ~/.dsh/ by default (overridable via DSH_HOME env var). The settings.yaml within controls model providers.

Steps

Setup (initial install)

  1. Run the install script
    bash ~/.agents/skills/dsh-setup/scripts/install.sh
    
    This script:
    • Verifies Node.js version meets DSH requirements
    • Installs pnpm locally if not present
    • Creates ~/.local/share/dsh/ and runs pnpm add @deepseek-ai/dsh
    • Approves required build scripts (node-pty, koffi, protobufjs)
    • Verifies the dsh binary works

Read the full file on GitHub · 167 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 167 lines · 29 tokens per session scan A fbd2b61c159f

Subscribe to this mod's changes

dsh-setup is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,913 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens