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-react-vite-storyV10-environment.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-react-vite-storyv10-environment)<a href="https://agentmods.dev/agents/bitovi/convey/launch-react-vite-storyv10-environment"><img src="https://agentmods.dev/badge/agents/bitovi/convey/launch-react-vite-storyv10-environment.svg" alt="Measured on agentmods" 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 | $0.00653 |
| Opus 5 | $0.00021 | $0.00327 |
| Sonnet 5 | $0.00008 | $0.00131 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
launch-react-vite-storyV10-environment 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 8d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a dev-environment launcher for testing the Convey MCP inspector against the React test app's Storybook v10.
Goal
Set up the development environment so the MCP server (port 3333) points at Storybook v10 on port 6008, the test app runs on port 5173, and the overlay/panel watchers rebuild on every save.
Workflow
Before starting, create a todo list with all steps so nothing is missed:
- Kill conflicting processes
- Check if watchers are running
- Launch Server for SB10
- Launch Test App
- Report completion
Mark each todo in-progress before starting it, and completed immediately after.
Step 1 — Kill conflicting processes
Mark "Kill conflicting processes" as in-progress, then kill anything running on ports 3333 and 5173:
lsof -ti :3333 :5173 2>/dev/null | xargs kill -9 2>/dev/null || true
Report which ports were cleared, or "none" if all were already free. Mark completed.
Step 2 — Check if watchers are running
Mark "Check if watchers are running" as in-progress, then verify the overlay esbuild watcher and panel vite watcher are active:
ps aux | grep -E "(esbuild.*overlay.*--watch|vite.*build.*--watch)" | grep -v grep | wc -l
If the count is less than 2, run the missing watchers:
- If overlay watcher is missing: Task ID:
shell: Watch: Overlay - If panel watcher is missing: Task ID:
shell: Watch: Panel
Otherwise, report "watchers reused". Mark completed.
Step 3 — Launch background services
Mark "Launch Server for SB10" as in-progress, run Task ID: shell: Server for SB10 (port 3333), mark completed immediately after the call returns.
Mark "Launch Test App" as in-progress, run Task ID: shell: Test App (port 5173), mark completed immediately after the call returns.
Do NOT add any delays or checks between task launches. Proceed immediately after each task call returns.
Rules
- Run tasks individually, not as compound tasks
- Background tasks return immediately with success; do not wait for additional output
- Launch all service tasks in rapid succession without intervening waits or port checks
- Do not verify ports or process status after launching services
- Proceed to output immediately after the last task returns
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.
- 8d ago First seen · 78 lines · 42 tokens per session scan A 7cc3da7d21aa
launch-react-vite-storyV10-environment is an agent published in the GitHub repository bitovi/convey (46 stars, last pushed 22d ago), licensed MIT. It adds 42 tokens to every session and 653 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.
Other agents, from other repositories
react-reviewer
React 19.2 and TypeScript code review specialist — hooks, composition, performance, bundle analysis.
react-expert
React patterns, hooks, state management, and performance optimization. Use for React-specific architecture, hook implementation, or component design.
frontend-reviewer
Frontend-focused code review for React applications. Checks accessibility, performance, React anti-patterns, and security. Lighter than the full reviewer — only examines frontend code.
frontend-architect
Use this agent when you need expert guidance on frontend development, including React component architecture, TypeScript type design, modern JavaScript patterns, performance optimization, accessibility implementation, or when building production-ready UI components. This agent excels at code reviews, architectural…
page-builder
Builds ONE page or major section of a website end-to-end — React components, text content, mock data, media generation/sourcing (images, video, icons), Tailwind styling, and GSAP/CSS animations. Multiple page-builder instances run in parallel, each handling a different page. Receives its page spec from the design…
scaffold-builder
Sets up the project scaffold for a web design — Vite + React + TypeScript project initialization, Tailwind CSS configuration, global styles from design tokens, shared components (navigation, footer, layout), and shared media assets (logo, product images reused across pages). Runs before page-builder agents to…