convey: Agent for Claude Code

.claude/agents/launch-external-6006-storybook-env.md

launch-external-6006-storybook-env is an agent for Claude Code from bitovi/convey. It costs 49 tokens per session (616 once invoked), scanned A, original, MIT.

A development-environment launcher for testing a Convey MCP inspector with an external Storybook, a tool for viewing and testing UI components. It starts the inspector, its file watchers, and a test app while leaving Storybook on port 6006 running.

In plain words
What is it for?
Clearing an old MCP server on port 3333, checking that the port is free, and starting the VS Code development task for the external Storybook setup.
Why use it?
It prepares the required local services and avoids accidentally stopping the external Storybook that the inspector needs to connect to.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is bitovi/convey's own configuration. It tells Claude Code how to work on convey itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything convey configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/bitovi/convey/main/.claude/agents/launch-external-6006-storybook-env.md
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-external-6006-storybook-env

README.md
[![agentmods](https://agentmods.dev/badge/agents/bitovi/convey/launch-external-6006-storybook-env/github.svg)](https://agentmods.dev/agents/bitovi/convey/launch-external-6006-storybook-env)
Your own site
<a href="https://agentmods.dev/agents/bitovi/convey/launch-external-6006-storybook-env"><img src="https://agentmods.dev/badge/agents/bitovi/convey/launch-external-6006-storybook-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.

agentmods 80×15 button for launch-external-6006-storybook-env

Your own site · 80×15
<a href="https://agentmods.dev/agents/bitovi/convey/launch-external-6006-storybook-env"><img src="https://agentmods.dev/badge/agents/bitovi/convey/launch-external-6006-storybook-env.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 616 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00049 $0.00616
Opus 5 $0.00024 $0.00308
Sonnet 5 $0.00010 $0.00123
Haiku 4.5 $0.00005 $0.00062

Measured 11d ago against content hash 4d89732038e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

launch-external-6006-storybook-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 11d 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-external-6006-storybook-env.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 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 an external project's Storybook running on port 6006.

Goal

Kill any conflicting process on port 3333 (old MCP server), then launch the Dev: External SB6006 compound VS Code task which starts:

  • Watch: Overlay (rebuilds overlay on save)
  • Watch: Panel (rebuilds panel on save)
  • Server for External SB (port 3333, STORYBOOK_URL=http://localhost:6006)
  • Test App (port 5173)

Do NOT kill port 6006. That is the user's external Storybook — leave it running.

Workflow

Step 1 — Kill conflicting process on port 3333

Run this command to kill any old MCP server on port 3333:

lsof -ti :3333 | xargs kill -9 2>/dev/null || true

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

Do NOT kill port 6006. That is the user's external Storybook.

Step 2 — Verify port 3333 is clear

lsof -iTCP:3333 -sTCP:LISTEN -P -n 2>/dev/null && echo "ERROR: port 3333 still in use" || echo "Port 3333 clear"

If port 3333 is still occupied, try killing again with kill -9. If it still fails, stop and report the error.

Step 3 — Tell the user to start tasks

Tell the user:

Port 3333 is clear. Run the Dev: External SB6006 task via Terminal → Run Task → Dev: External SB6006 to start all services.

This launches four processes in dedicated terminal panels:

  • Watch: Overlay — rebuilds overlay/dist/overlay.js on save
  • Watch: Panel — rebuilds panel/dist/ on save
  • Server for External SB (port 3333) — MCP server proxying to Storybook at http://localhost:6006
  • Test App (port 5173) — Vite dev server

Once running, open http://localhost:3333/panel/ for the inspector.

Rules

  • If any step fails, stop and report the error — do not continue.
  • The user is responsible for starting their own Storybook on port 6006. This agent only ensures the port is clear and tells the user how to launch the MCP infrastructure.
  • Always report what was killed and what is now running.

Read the full file on GitHub · 61 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. 11d ago First seen · 61 lines · 49 tokens per session scan A 4d89732038e6

Subscribe to this mod's changes

launch-external-6006-storybook-env is an agent published in the GitHub repository bitovi/convey (46 stars, last pushed 25d ago), licensed MIT. It adds 49 tokens to every session and 616 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

vue-nuxt-expert

Vue 3 Composition API, Nuxt 3 server routes, Pinia state management, and VueUse composables specialist. Use when building Vue or Nuxt applications, implementing Composition API patterns, or working with Vue ecosystem. Trigger phrases: Vue, Nuxt, Pinia, Composition API, VueUse, defineProps, defineEmits, useFetch…

travisjneuman/.claude · 90 tokens

pwa-specialist

Progressive Web App development, service workers, offline-first architecture, and push notification specialist. Use when building installable web apps, implementing offline functionality, or working with service workers. Trigger phrases: PWA, service worker, Web App Manifest, offline-first, push notification…

travisjneuman/.claude · 76 tokens

design-master

Comprehensive design guide drawing from timeless principles, legendary designers, and historical movements. Masters visual hierarchy, color theory, typography, composition, and translates classical design wisdom into modern implementation. Use PROACTIVELY for any UI/UX design, component creation, or visual…

HermeticOrmus/LibreUIUX-Claude-Code · 59 tokens

drupal-site-builder

Drupal site builder for configuring content types, fields, taxonomy, menus, paragraphs, and search. Use for configuration-layer tasks that don't require custom PHP.

edutrul/drupal-ai · 35 tokens

gsp-polisher

Detects and fixes AI-slop craft failures in React/Tailwind codebases. Spawned by /gsp-polish.

jubscodes/get-shit-pretty · 31 tokens

gsp-accessibility-auditor

Audits designs and code for WCAG 2.2 AA/AAA compliance. Spawned by /gsp-accessibility or /gsp-project-critique.

jubscodes/get-shit-pretty · 42 tokens