docker-compose-launch

docker-compose-launch is a skill for Claude Code, Codex from aliengiraffe/vigilante. It costs 24 tokens per session (501 once invoked), scanned A, original, Apache-2.0.

A helper for starting local services with Docker Compose, a tool that runs services such as databases in containers. It is scoped to a project worktree, an isolated working copy of the code.

In plain words
What is it for?
Use it to launch MySQL, MariaDB, PostgreSQL, or MongoDB when an implementation workflow requires those services.
Why use it?
It provides database dependencies needed before an application can start, run migrations, or execute tests, while keeping them tied to the assigned worktree.

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/aliengiraffe/vigilante/docker-compose-launch
Any agent
npx skills add aliengiraffe/vigilante --skill docker-compose-launch
Clone the repo
git clone --depth 1 https://github.com/aliengiraffe/vigilante

Made for: Claude Code, Codex.

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 docker-compose-launch

README.md
[![agentmods](https://agentmods.dev/badge/skills/aliengiraffe/vigilante/docker-compose-launch.svg)](https://agentmods.dev/skills/aliengiraffe/vigilante/docker-compose-launch)
Your own site
<a href="https://agentmods.dev/skills/aliengiraffe/vigilante/docker-compose-launch"><img src="https://agentmods.dev/badge/skills/aliengiraffe/vigilante/docker-compose-launch.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 501 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 $0.00024 $0.00501
Opus 5 $0.00012 $0.00251
Sonnet 5 $0.00005 $0.00100
Haiku 4.5 $0.00002 $0.00050

Measured 5d ago against content hash 4e89fae705e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docker-compose-launch 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 5d 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.

skills/docker-compose-launch/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docker Compose Launch

Overview

Use this skill only when the selected implementation workflow explicitly needs local services before app startup, migrations, or tests can run. Keep all service startup scoped to the assigned worktree and treat Docker Compose as a reusable helper for local implementation and test dependencies only.

Invocation Contract

The parent implementation skill should pass or infer this contract before acting:

  • required: true or false
  • worktree_path: absolute path to the assigned worktree
  • service_types: one or more of mysql, mariadb, postgres, or mongodb
  • reason: short explanation of which app, package, migration, or test command needs the services
  • preferred_mechanism: repository-native compose file, repo script, or fallback compose generation

If required is false, return status: not_needed and do nothing else.

Execution Rules

  • Prefer repository-owned docker-compose.yml, docker-compose.yaml, compose.yml, or compose.yaml files before generating new files.
  • Prefer repository scripts or task-runner commands that already wrap Compose when they are documented and usable.
  • Namespace any generated project name, file, network, volume, or container identifiers to the assigned worktree.
  • Wait for service readiness before reporting success.
  • Surface the exact startup and teardown commands that were used.

Structured Result

Return a concise structured summary using these fields:

  • status: ready, not_needed, or failed
  • services: services that were started or detected
  • mechanism: repo_compose, repo_script, or generated_fallback
  • commands: startup, readiness, and teardown commands
  • connection: host, port, database, username, URL, or env hints when available
  • cleanup: explicit stop command, or none
  • artifacts: compose files or env files created or reused
  • notes: concise caveats or follow-up steps

Guardrails

  • Do not launch services outside the assigned worktree scope.
  • Do not assume every repository needs Docker Compose.
  • Do not replace a documented repository-native startup flow with a generated one unless the native path is unusable.
  • Do not claim success until the requested service is accepting connections.

Read the full file on GitHub · 46 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 46 lines · 24 tokens per session scan A 4e89fae705e0

Subscribe to this mod's changes

docker-compose-launch is a skill published in the GitHub repository aliengiraffe/vigilante (39 stars, last pushed 2d ago), licensed Apache-2.0. It adds 24 tokens to every session and 501 once invoked, about $0.0001 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.