A command for managing a project's local development server—the server used to run an app on your own computer while you build it.

Use it to start, stop, or restart the server. It checks package.json and common configuration files, and asks for the command when it cannot find one.

It avoids remembering the right start command and port, and lets you control the server from one command.

dev-server — Command by vthinkdeveloper

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 commands/vthinkdeveloper/vthink-agent-toolkit/dev-server

Clone the repo

git clone --depth 1 https://github.com/vthinkdeveloper/vthink-agent-toolkit

Made for: Claude Code.

Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 753 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.

Model	Per session	Once invoked
Fable 5	$0.00053	$0.00753
Opus 5	$0.00026	$0.00377
Sonnet 5	$0.00011	$0.00151
Haiku 4.5	$0.00005	$0.00075

Measured yesterday against content hash 5312ca0b6dfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-server 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 yesterday.

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/commands/dev-server.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Server — Start / Stop / Restart

Manage the local development server. Supports three actions: start, stop, restart.

Step 1: Parse the Action

Read $ARGUMENTS to determine the action: start, stop, or restart.

If no argument is provided or the argument is unrecognized, ask the user:

"What would you like to do? start / stop / restart"

Step 2: Detect Server Config

Auto-detect the start command and port from the project:

Read package.json — look for:
- scripts.start — the start command (e.g., node server.js, react-scripts start)
- scripts.dev — alternative dev command (prefer dev over start for frontend projects)
- Any PORT env var references in the scripts
Check for common config files — look for port in:
- .env or .env.local — PORT=<number>
- vite.config.js / webpack.config.js — port: field
- server.js / app.js / index.js — listen(<port>)
Default fallback — if no port is found, assume 3000 but inform the user.
If no start command found — ask the user:

"I couldn't find a start command. What command starts your server? (e.g., npm run dev, python manage.py runserver)"

Step 3: Execute the Action

start

Check if the detected port is already in use:
```
lsof -ti:<port>
```
If the port is occupied, inform the user:

"Port is already in use (PID ). Run /dev-server stop first, or check if another instance is running." Stop here — do NOT start a second instance.
If the port is free, start the server in the background:
```
<start-command> &
```
Wait 2 seconds, then verify the process is still running.
Confirm to the user: "Server started on port . Running in background — you can keep using Claude Code."

stop

Find the process using the detected port:
```
lsof -ti:<port>
```
If a process is found, kill it:
```
kill $(lsof -ti:<port>)
```
Confirm: "Server stopped (port is now free)."
If nothing was running: "No server was running on port ."

Read the full file on GitHub · 82 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.

yesterday First seen · 82 lines · 53 tokens per session scan A 5312ca0b6dfb

Subscribe to this mod's changes

dev-server is a command published in the GitHub repository vthinkdeveloper/vthink-agent-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 753 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 2026-08-31.

Productivity dev-server local npm port workflow

dev-server

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Dev Server — Start / Stop / Restart

Step 1: Parse the Action

Step 2: Detect Server Config

Step 3: Execute the Action

start

stop

What this file has done since we first saw it

Other commands, from other repositories

pr-address

enforce_standards

OPSX: Sync

context

OPSX: Verify

OPSX: Continue