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/brevdev/workshop-build-an-agent/setup-workshopnpx skills add brevdev/workshop-build-an-agent --skill setup-workshopgit clone --depth 1 https://github.com/brevdev/workshop-build-an-agentWhat 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 | $0.00210 | $0.02385 |
| Opus 5 | $0.00105 | $0.01192 |
| Sonnet 5 | $0.00042 | $0.00477 |
| Haiku 4.5 | $0.00021 | $0.00238 |
Grade B, and why
setup-workshop scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
are handled by setup. If sudo is not passwordless, run `sudo -v` now — the How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set Up & Run the Build-an-Agent Workshop Locally
Bring a local Linux NVIDIA GPU machine from bare to a browser-accessible DevX-Lab — the workshop's JupyterLab environment for all seven modules. This reproduces the Brev cloud deployment minus its cloud-only plumbing: no cloud-user detection, and the nginx single-port router + systemd auto-start are optional rather than default (local users reach the app directly via the Workbench proxy URL).
Outcome
A running DevX-Lab reachable at
http://localhost:<proxyPort>/projects/<name>/applications/DevX-Lab/
(proxyPort defaults to 10000). On a desktop it can auto-open; on a headless box
it is reached via SSH port-forward.
When to use / not use
Use on a local Linux host with an NVIDIA GPU (x86_64 or aarch64). Trigger
on requests to set up / install / deploy / spin up / run the workshop or
DevX-Lab locally. Do not use this to provision a Brev cloud instance — that
is the brev-cli / nvwb Brev path; this skill is the local analog of the Brev
startup script.
Running in an OpenShell/NemoClaw sandbox? This installer needs sudo,
Docker, and the Workbench download host — all unavailable there; it fails by
design, not by bug. Use the sandbox-native pair instead:
setup-workshop-nemoclaw (agent inside the sandbox) +
setup-workshop-nemoclaw-operator (host side: policy, secrets, port-forward).
Required input
- NVIDIA API key (mandatory). Free at https://build.nvidia.com (log in → "Get API Key"). Every module calls NVIDIA NIM/Nemotron with it. The build succeeds without it, but every model call then returns 401.
- Optional:
TAVILY_API_KEY(Module 1 web search),LANGSMITH_API_KEY(Module 3 tracing). - Note:
secrets.envis gitignored, so a fresh clone never contains keys — they must be supplied. Prompt the user for the NVIDIA key if it is not already provided or present in an existingsecrets.env.
Procedure
Drive these steps in order. Each script lives in scripts/. Report progress and
the final URL to the user.
What ships with it
9 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.
- assets/nginx-workshop.conf.template 2.0 KB
- assets/nvwb-workshop.service.template 921 B
- assets/secrets.env.template 1.1 KB
- references/access.md 2.4 KB
- references/persistence.md 3.0 KB
- references/troubleshooting.md 5.2 KB
- scripts/preflight.sh 4.1 KB runs code
- scripts/setup.sh 6.7 KB runs code
- scripts/start-app.sh 2.3 KB runs code
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 · 180 lines · 210 tokens per session scan B d4ebf7509461
setup-workshop is a skill published in the GitHub repository brevdev/workshop-build-an-agent (133 stars, last pushed 14d ago), licensed Apache-2.0. It adds 210 tokens to every session and 2,385 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
traceway-setup
Analyze and instrument repositories for Traceway observability. Use when the user wants to plan, add, migrate, or verify Traceway or OpenTelemetry monitoring for backend, browser, full-stack, mobile or iOS, or AI-agent software, including project topology and user-approved setup-plan creation. Backends use OTLP/HTTP…
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.