launch-demo-env

launch-demo-env is an agent for Claude Code from bitovi/convey. It costs 42 tokens per session (702 once invoked), scanned A, original, MIT.

A development environment launcher for a static Convey demo site with Storybook. Storybook is a tool for developing and previewing interface components separately.

In plain words
What is it for?
It helps build the demo and Storybook, watch for code changes, and serve the result on port 4000.
Why use it?
It handles the build, file watching, and local serving needed to test the demo and its Storybook integration together.

Agent for Claude Code

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 agents/bitovi/convey/launch-demo-env
Clone the repo
git clone --depth 1 https://github.com/bitovi/convey

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for launch-demo-env

README.md
[![agentmods](https://agentmods.dev/badge/agents/bitovi/convey/launch-demo-env.svg)](https://agentmods.dev/agents/bitovi/convey/launch-demo-env)
Your own site
<a href="https://agentmods.dev/agents/bitovi/convey/launch-demo-env"><img src="https://agentmods.dev/badge/agents/bitovi/convey/launch-demo-env.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 702 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 $0.00042 $0.00702
Opus 5 $0.00021 $0.00351
Sonnet 5 $0.00008 $0.00140
Haiku 4.5 $0.00004 $0.00070

Measured 4d ago against content hash c6f336cc6512, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

launch-demo-env 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 4d 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.

.claude/agents/launch-demo-env.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a dev-environment launcher for the Convey static demo site.

Goal

Build the demo (including Storybook), start a watch process for rebuilds on code changes, and serve the build output on port 4000 so the user can test the demo with Storybook integration.

Why port 4000?

The Vite dev server (npx vite on port 5173) does not include the Storybook build. The demo's fetch interceptor expects a static Storybook build at /storybook/, which only exists in the demo/dist/ output after npm run build. Serving the built output on port 4000 is the only way to test the demo with Storybook locally.

Workflow

Step 1 — Kill conflicting process on port 4000

lsof -ti :4000 | xargs kill -9 2>/dev/null || true

Report which PIDs were killed, or "none" if port was clear.

Step 2 — Verify port 4000 is clear

lsof -iTCP:4000 -sTCP:LISTEN -P -n 2>/dev/null && echo "ERROR: port 4000 still in use" || echo "Port 4000 clear"

If still occupied, try killing again. If it still fails, stop and report the error.

Step 3 — Run the full demo build (including Storybook)

cd demo && npm run build

This runs vite build then builds Storybook into demo/dist/storybook/. This step can take a while (Storybook build is slow). Wait for it to complete before proceeding.

Step 4 — Start the watch and serve tasks

Run each of these VS Code tasks individually:

  • Task ID: shell: Demo: Watch
  • Task ID: shell: Demo: Serve (port 4000)

Step 5 — Report

Tell the user:

Demo built and served. Open http://localhost:4000 to use the demo with Storybook.

Running tasks:

  • Demo: Watchvite build --watch rebuilds demo/dist/ on code changes (without clearing the Storybook build)
  • Demo: Serve (port 4000)http-server serves the static build

Note: If you change test-app stories, you need to re-run npm run build:storybook in the demo/ directory to update the Storybook build.

Rules

  • Always build storybook before starting the watch process. The watch process (vite build --watch) does NOT empty dist/ — the cleanDist Vite plugin skips cleanup when --watch is in argv — so the storybook build in dist/storybook/ is preserved across restarts and rebuilds.
  • Always run tasks individually — never use compound tasks.
  • If any step fails, stop and report the error — do not continue.
  • Always report what was killed and the build status.

Read the full file on GitHub · 68 lines

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. 4d ago First seen · 68 lines · 42 tokens per session scan A c6f336cc6512

Subscribe to this mod's changes

launch-demo-env is an agent published in the GitHub repository bitovi/convey (46 stars, last pushed 18d ago), licensed MIT. It adds 42 tokens to every session and 702 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories