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.
npx agentmods add skills/rhtevan/agentfs/dsh-setupnpx skills add rhtevan/agentfs --skill dsh-setupgit clone --depth 1 https://github.com/rhtevan/agentfsWhat 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.
| Model | Per session | Once 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 |
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.
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.
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)
- Run the install script
This script:bash ~/.agents/skills/dsh-setup/scripts/install.sh- Verifies Node.js version meets DSH requirements
- Installs pnpm locally if not present
- Creates
~/.local/share/dsh/and runspnpm add @deepseek-ai/dsh - Approves required build scripts (node-pty, koffi, protobufjs)
- Verifies the
dshbinary works
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.
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.
- 2d ago First seen · 167 lines · 29 tokens per session scan A fbd2b61c159f
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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…
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.
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.