dev-environments

A guide to the development service combinations used for testing an MCP Storybook add-on. It explains which servers, file watchers, test apps, Storybook versions, frameworks, and ports belong together.

In plain words
What is it for?
Running the general test app, Storybook 8 or 10, Tailwind 3, Angular, and their related MCP servers and test applications.
Why use it?
It removes guesswork when choosing and starting the right local services for a particular test scenario.

Skill for Claude CodeCodex

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 skills/bitovi/convey/dev-environments
Any agent
npx skills add bitovi/convey --skill dev-environments
Clone the repo
git clone --depth 1 https://github.com/bitovi/convey

Made for: Claude Code, Codex.

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,596 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 $0.00068 $0.02596
Opus 5 $0.00034 $0.01298
Sonnet 5 $0.00014 $0.00519
Haiku 4.5 $0.00007 $0.00260

Measured 2d ago against content hash 1a37658daae8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-environments 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 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.

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.

.github/skills/dev-environments/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Development Environments

This project has multiple test apps, Storybook versions, and server configurations. Different features require different combinations of services.

Quick Reference — Compound Tasks

Run via Terminal → Run Task:

Task What it starts Use when
Dev: Test App Overlay watch, Panel watch, Server (3333), Test App (5173) General development, overlay/panel work
Dev: SB8 Overlay watch, Panel watch, Server (3333→SB 6007), SB8 (6007), Test App (5173) Testing Storybook 8 addon integration
Dev: SB10 Overlay watch, Panel watch, Server (3333→SB 6008), SB10 (6008), Test App (5173) Testing Storybook 10 addon integration
Dev: All v3 Overlay watch, Panel watch, Server v3 (3334), Test App v3 (5175) Testing Tailwind v3 support
Dev: Angular Overlay watch, Panel watch, Server Angular (3335), Test App Angular (5177) Testing Angular 21 support
Dev: SB Angular Overlay watch, Panel watch, Server Angular (3335→SB 6009), SB Angular (6009), Test App Angular (5177) Testing Angular Storybook addon

Port Map

Port Service Notes
3333 MCP Server Always runs from test-app/ cwd (resolves TW v4)
3334 MCP Server v3 Runs from test-app-v3/ cwd (resolves TW v3)
5173 Test App Tailwind v4 React app
5174 Panel dev Only for panel-only dev (cd panel && npm run dev)
5175 Test App v3 Tailwind v3 React app
5176 Test App Astro Astro framework test app
6006 Panel Storybook Panel component stories (internal dev)
6007 SB8: Test App Storybook 8 with test-app stories + Convey addon
6008 SB10: Test App Storybook 10 with test-app stories + Convey addon
3335 MCP Server Angular Runs from test-app-angular/ cwd (resolves TW v4)
5177 Test App Angular Angular 21 + Tailwind v4 app
6009 SB10: Angular Storybook 10 with Angular test-app stories + Convey addon

Read the full file on GitHub · 252 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. 2d ago First seen · 252 lines · 68 tokens per session scan A 1a37658daae8

Subscribe to this mod's changes

dev-environments is a skill published in the GitHub repository bitovi/convey (46 stars, last pushed 16d ago), licensed MIT. It adds 68 tokens to every session and 2,596 once invoked, about $0.0003 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.