voltron-lions

Mission-style multi-agent orchestration: Voltron Main coordinates four specialist Lions (Red/Blue/Green/Yellow) to execute objectives with structured briefs, file-ownership boundaries, skills-gap detection, and risk registers.

Packages

Package details

skillprompt

Install voltron-lions from npm and Pi will load the resources declared by the package manifest.

$ pi install npm:voltron-lions
Package
voltron-lions
Version
0.3.0
Published
Aug 18, 2026
Downloads
158/mo · 9/wk
Author
voltron-5
License
MIT
Types
skill, prompt
Size
53.9 KB
Dependencies
0 dependencies · 0 peers
Pi manifest JSON
{
  "skills": [
    "./skills"
  ],
  "prompts": [
    "./prompts"
  ]
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

Voltron-Lions (pi package)

Mission-style multi-agent orchestration for the pi coding agent. One prompt forms Voltron — a commander (Black Lion) who plans, delegates, gates, and reports while playing four specialist Lion roles.

Install

pi install npm:voltron-lions
# or from git:
pi install git:github.com/Cloudscockpit/voltron-lions-claudecode

Use

Run the start-mission prompt with an objective:

start voltron mission <objective>

Voltron Main will:

  1. Draft a Mission Brief (objective, scope, success criteria, constraints)
  2. Send Green Lion on read-only recon
  3. Generate Lion Assignments with strict file-ownership boundaries
  4. Perform Skills Gap analysis against the shipped skills registry & actions map
  5. Build a Risk Register (technical / scope / integration / data-loss, severity L/M/H)
  6. Wait for your go / no-go, then execute as Red / Blue / Yellow Lions

What ships in this package

  • Prompts: start-mission
  • Skills: skills-registry, actionboard-onboarding, actionboard-pod-connect, browser-actions, cowork-mcp-connect

Note: pi loads the skills/ and prompts/ directories. The agents/ and commands/ folders target Claude Code / Cowork and are ignored by pi (this is a dual-target plugin).

License

MIT © Cloudscockpit