start-server

start-server is a skill for Claude Code from thenativeweb/claude-plugins. It costs 67 tokens per session (787 once invoked), scanned A, original, MIT.

A procedure for starting or stopping a temporary EventSourcingDB server, a database that stores changes as events, in Docker for local development.

In plain words
What is it for?
Use it to try EventSourcingDB locally, test integrations, or shut down the development server.
Why use it?
It provides a disposable test database with a web interface and simple access settings; its data is lost when the container stops.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the esdb plugin — 11 skills shipped together

Good fit Use it to try EventSourcingDB locally, test integrations, or shut down the development server.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thenativeweb/claude-plugins/start-server
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.

Any agent
npx skills add thenativeweb/claude-plugins --skill start-server
Clone the repo
git clone --depth 1 https://github.com/thenativeweb/claude-plugins

Made for: Claude Code.

Or install esdb, the plugin that ships this one along with the rest of its 11 skills.

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 start-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/thenativeweb/claude-plugins/start-server/github.svg)](https://agentmods.dev/skills/thenativeweb/claude-plugins/start-server)
Your own site
<a href="https://agentmods.dev/skills/thenativeweb/claude-plugins/start-server"><img src="https://agentmods.dev/badge/skills/thenativeweb/claude-plugins/start-server/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 start-server

Your own site · 80×15
<a href="https://agentmods.dev/skills/thenativeweb/claude-plugins/start-server"><img src="https://agentmods.dev/badge/skills/thenativeweb/claude-plugins/start-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 787 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00067 $0.00787
Opus 5.5 $0.00027 $0.00315
Sonnet 5.5 $0.00013 $0.00157
Haiku 4.5 $0.00007 $0.00079

Measured 1mo ago against content hash e8447830bdba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

start-server scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -i "http://localhost:3000/api/v1/ping"
plugins/esdb/skills/start-server/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start Server (Development Mode)

Run a local EventSourcingDB instance for development and testing via Docker. The instance uses:

  • Temporary data storage (--data-directory-temporary) – all data is lost when the container stops.
  • Plain HTTP instead of HTTPS (--http-enabled --https-enabled=false).
  • The built-in web UI (--with-ui).
  • A simple API token (secret).

This setup is for development only. Never use it in production.

Defaults

  • Container name: eventsourcingdb-dev
  • Port: 3000
  • API token: secret
  • Image: thenativeweb/eventsourcingdb:latest

If the user asks for a different port, token, or image version, use their values instead.

Preflight

Check that Docker is running, and whether a dev instance already exists or the port is taken:

docker info > /dev/null 2>&1 && echo "Docker: running" || echo "Docker: NOT running"
docker ps --all --filter "name=eventsourcingdb-dev" --format "{{.Names}} ({{.Status}})"
lsof -nP -iTCP:3000 -sTCP:LISTEN || echo "Port 3000 is free"
  • If Docker is not running, ask the user to start Docker first, then stop.
  • If a container named eventsourcingdb-dev is already running, do not start a second one. Inform the user that the instance is already available and report the connection details (see below).
  • If the port is taken by another process, use AskUserQuestion to ask the user for an alternative port.

Start

docker run -d --rm --name eventsourcingdb-dev -p 3000:3000 \
  thenativeweb/eventsourcingdb:latest run \
  --api-token=secret \
  --data-directory-temporary \
  --http-enabled \
  --https-enabled=false \
  --with-ui

When using a custom port, only change the host side of the mapping (e.g., -p 3001:3000); the container-internal HTTP port stays 3000.

Verify

Wait briefly, then ping the instance:

sleep 2
curl -s -i "http://localhost:3000/api/v1/ping"

Check that the response contains HTTP status 200 OK and the Server header starts with EventSourcingDB/. If the ping fails, inspect the logs with docker logs eventsourcingdb-dev and report the problem.

Read the full file on GitHub · 91 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. 1mo ago First seen · 91 lines · 67 tokens per session scan A e8447830bdba

Subscribe to this mod's changes

start-server is a skill published in the GitHub repository thenativeweb/claude-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 787 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

deployment

Deploy Memoria with Docker Compose or Kubernetes. Environment variables, multi-instance setup, security. Use when deploying or configuring Memoria.

matrixorigin/memoria · 28 tokens

polar-local-environment

This skill should be used when setting up or managing Polar local development environment with Docker.

fcakyon/claude-codex-settings · 22 tokens

postgres-container-ops

PostgreSQL container operations for the docker instance: volume persistence audit (PGDATA layout and the PG18 version-specific data-directory change), /dev/shm sizing (shmsize), pgisready healthcheck tuning, minor-version pin policy (16-alpine to explicit 16.x-alpine), the major-version upgrade runbook (pgupgrade…

fmflurry/settings-opencode · 151 tokens

postgres-health-check

Read-only PostgreSQL instance health battery: connectivity/uptime, cache hit ratio, dead tuples & autovacuum hotspots, XID wraparound distance, long-running & idle-in-transaction sessions, unused indexes, checkpoint stats, archiver health, connection count vs maxconnections, and docker container/volume checks. Use…

fmflurry/settings-opencode · 118 tokens

postgres-performance-tuning

PostgreSQL performance tuning for the docker instance: memory sizing vs the 1g memlimit (sharedbuffers, effectivecachesize, workmem math), checkpoint tuning (maxwalsize, checkpointcompletiontarget, pgstatcheckpointer), pgstatstatements enablement via compose, slow-query triage, EXPLAIN (ANALYZE, BUFFERS)…

fmflurry/settings-opencode · 160 tokens

postgres-backup-restore

PostgreSQL backup & restore playbook for the docker instance: pgdump/pgdumpall recipes, WAL archiving + PITR setup (archivemode, archivecommand, recovery.signal, recoverytargettime, timelines), restore drills, and the PG16 no-incremental-backup constraint. Use when asked about backup, restore, PITR, pgdump…

fmflurry/settings-opencode · 113 tokens