Borrowing it
Nothing to install: this file belongs to bitovi/convey. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bitovi/convey/main/.claude/agents/launch-demo-env.mdgit clone --depth 1 https://github.com/bitovi/conveyWrote 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.
[](https://agentmods.dev/agents/bitovi/convey/launch-demo-env)<a href="https://agentmods.dev/agents/bitovi/convey/launch-demo-env"><img src="https://agentmods.dev/badge/agents/bitovi/convey/launch-demo-env/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.00702 |
| Opus 5.5 | $0.00017 | $0.00281 |
| Sonnet 5.5 | $0.00008 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
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 2mo 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 — 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: Watch —
vite build --watchrebuildsdemo/dist/on code changes (without clearing the Storybook build)- Demo: Serve (port 4000) —
http-serverserves the static buildNote: If you change test-app stories, you need to re-run
npm run build:storybookin thedemo/directory to update the Storybook build.
Rules
- Always build storybook before starting the watch process. The watch process (
vite build --watch) does NOT emptydist/— thecleanDistVite plugin skips cleanup when--watchis in argv — so the storybook build indist/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.
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.
- 2mo ago First seen · 68 lines · 42 tokens per session scan A c6f336cc6512
launch-demo-env is an agent published in the GitHub repository bitovi/convey (47 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 702 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
srd-creator
Crear SRDs, especificaciones técnicas desde PRD. Invocar cuando technical spec, SRD, PRD to technical.
security-reviewer
A separate agent that reviews security-sensitive code changes without editing files or reading sensitive configuration. It focuses on authentication, permissions, payments, deletion, and handling of outside input.
skill-analyzer
Deep analysis agent for skill quality review. Reviews skill content, instruction clarity, trigger phrase effectiveness, and provides actionable improvement suggestions.
security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.