Skip to content
Back to skills

Run

ASecurity

Plan or launch the fleet locally: compose-first per service, with stdout tee'd to logDir so /debug can read it later.

  • 2 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 29, 2026
developmentpythonbashspringdocker

Works with

  • claude code
  • mcp

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 29, 2026

npx -y skills add talayash/spring-fleet --skill run --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Run?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Run
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/talayash-run/badge)](https://www.skillsdirectory.com/skills/talayash-run)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: run
description: Plan or launch the fleet locally: compose-first per service, with stdout tee'd to logDir so /debug can read it later.
argument-hint: [service|all] [--execute]
allowed-tools: Bash, Read
disable-model-invocation: true
---

Plan or launch the Spring Boot fleet locally.

Input: `$ARGUMENTS`: optional bare service name (default: all), plus optional
`--execute` to actually start the processes (default: print the plan only).

Per-service resolution (from `services[].stack` produced by `/fleet-init`):
- `dockerCompose=true` → `docker compose up -d` in the repo (Spring Boot
  Docker Compose support discovers `compose.yaml` and wires `@ServiceConnection`
  beans automatically, the modern local-dev default).
- otherwise → `gradle bootRun` or `mvn spring-boot:run`, with stdout/stderr
  tee'd to `<logDir>/<service>.log` so `/debug` and `/logs` work without any
  logback changes.

Steps:
1. Locate `spring-fleet.config.json` (cwd, else suggest `/fleet-init`).
2. **Plan first** (no `--execute`):
   ```
   python "${CLAUDE_PLUGIN_ROOT}/scripts/run_fleet.py" --config ./spring-fleet.config.json [--service NAME]
   ```
   Show the JSON plan. Each entry has: `service`, `cwd`, `mode` (compose / gradle / maven),
   `command`, `logPath`, and `tee` (whether stdout will be redirected).
3. **Confirm with the user** before executing; launching processes is not
   reversible and may bind to fleet ports already in use.
4. **Execute** with `--execute` when the user approves:
   ```
   python "${CLAUDE_PLUGIN_ROOT}/scripts/run_fleet.py" --config ./spring-fleet.config.json --execute [--service NAME]
   ```
   Each spawned process is detached. Stop them with the usual OS tools (or
   `docker compose down` for compose-managed services).
5. After launch, suggest `/logs --follow` (or `tail_service_log` MCP tool)
   to confirm services are healthy.

## Outside Claude Code

- `${CLAUDE_PLUGIN_ROOT}` is the spring-fleet plugin root. Claude Code fills it in; in Codex it is the folder two directories above this SKILL.md.
- `$ARGUMENTS` is the text the user supplied with the request.
- spring-fleet MCP tools: pass `config_path` (absolute path of the project's `spring-fleet.config.json`). Codex starts the server outside the project, so it cannot find the config on its own.

Files in this skill

  • SKILL.md2.2 KB
  • agents/openai.yaml125 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.