legion
v8.0.6Official Codex plugin bundle for Legion's multi-agent planning, execution, review, and shipping workflows.
By 9thLevelSoftwareLicense: MIT79 GitHub starsUpdated last month
Directory evidence
- Runtimes
- Codex
- Parsed components
- 31 skill or MCP entries
- Source updated
- Sep 16, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install legion for Codex
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add legion@agent-plugin-marketplacePaste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.
Compatibility: the page URL and API slug “legion-2” remain stable.
- Codex:
legion-2@agent-plugin-marketplace→legion@agent-plugin-marketplace
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/9thLevelSoftware/legionClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.
Plugin files
├── .codex-plugin/plugin.json├── skills/agent-creator/SKILL.md├── skills/agent-registry/SKILL.md├── skills/authority-enforcer/SKILL.md├── skills/board-of-directors/SKILL.md├── skills/cli-dispatch/SKILL.md├── skills/codebase-mapper/SKILL.md├── skills/design-workflows/SKILL.md├── skills/execution-tracker/SKILL.md├── skills/github-sync/SKILL.md├── skills/hooks-integration/SKILL.md├── skills/intent-router/SKILL.md├── skills/legion/SKILL.md├── skills/marketing-workflows/SKILL.md├── skills/memory-manager/SKILL.md├── skills/milestone-tracker/SKILL.md├── skills/phase-decomposer/SKILL.md├── skills/plan-critique/SKILL.md├── skills/polymath-engine/SKILL.md├── skills/portfolio-manager/SKILL.md├── skills/questioning-flow/SKILL.md├── skills/review-evaluators/SKILL.md├── skills/review-loop/SKILL.md├── skills/review-panel/SKILL.md├── skills/security-review/SKILL.md├── skills/ship-pipeline/SKILL.md├── skills/spec-pipeline/SKILL.md├── skills/wave-executor/SKILL.md├── skills/workflow-common/SKILL.md├── skills/workflow-common-domains/SKILL.md├── skills/workflow-common-github/SKILL.md└── skills/workflow-common-memory/SKILL.md
Included Skills31
Guided agent personality creation with schema validation and registry integration
Maps all 48 Legion agents by division, capability, and task type for intelligent team assembly
Validates and enforces agent authority boundaries during wave execution and review panels
Governance escalation tier with dynamic agent panels, deliberation, voting, and audit persistence
Cross-CLI dispatch infrastructure for routing work to external CLIs
Engine for /legion:map. Analyzes an existing codebase, generates CODEBASE.md for backward-compatible architecture context, and writes .planning/codebase/ index artifacts consumed by /legion:start, /plan, /build, /review, /status, and /quick.
Design system creation, UX research workflows, and three-lens design review cycles for design-focused phases
Tracks execution progress with STATE.md updates, ROADMAP.md progress, and atomic git commits per plan
GitHub integration — issue tracking, PR creation, milestone sync, and status readback via gh CLI
Claude Code hooks for automated Legion lifecycle events
Interprets --just-* and --skip-* command flags for /legion:build and /legion:review, validates flag combinations against rules, and resolves the matching team template from intent-teams.yaml. Use when the user passes intent flags to build or review commands, asks about flag combinations, or needs to filter agent teams by intent.
Bridge Codex requests to the Legion workflows in this repository when the user references Legion or legacy /legion:* commands.
Marketing campaign planning — campaign documents, content calendars, cross-channel coordination, and marketing-specific phase decomposition
Stores and retrieves task outcomes and agent performance across sessions via .planning/memory/OUTCOMES.md, scores recalled entries by recency and importance, and degrades gracefully when memory files are absent. Use when the user references past sessions, asks to recall previous results, records lessons learned, or is working within a Legion multi-agent workflow.
Milestone management — definition, completion with metrics, archiving, summary generation
Breaks down a roadmap phase into phased implementation plans grouped by dependency order, assigns specialist agents to each plan, and generates PLAN.md files. Core engine for /legion:plan. Use when the user wants to plan a project phase, create implementation plans, organize work into waves, or assign agents to tasks.
Pre-mortem analysis and assumption hunting for stress-testing plans before execution
Research-first design discovery engine for /legion:explore
Multi-project portfolio management — registry, state aggregation, dependencies, agent allocation
Adaptive project initialization questioning that captures vision, requirements, and preferences
Multi-pass specialized evaluators for deep code quality, UI/UX, integration, and business logic review
Dev-QA loop engine with structured feedback, fix routing, and user escalation for /legion:review
Assembles a review panel of specialist agents matched to the code or artifact being reviewed, each evaluating against domain-specific rubrics, then synthesizes findings into a consolidated report. Called by review-loop for /legion:review. Use when the user needs multi-reviewer feedback, peer review simulation, rubric-based code evaluation, or expert critique from multiple perspectives.
OWASP Top 10 and STRIDE threat modeling security review for code and architecture
Pre-ship quality gates, deployment verification, and canary monitoring for the /legion:ship command
Pre-coding specification pipeline that produces structured spec documents through 5 stages
Executes wave-structured plans with personality-injected agents — parallel or sequential per CLI adapter
DEPRECATED compatibility shim; workflow-common-core is canonical for all conventions referenced here
Optional cross-domain conventions for design/marketing/specialized workflows
Optional GitHub interaction conventions shared across commands
Optional memory conventions shared across commands
Plugin manifests1
{
"name": "legion",
"version": "8.0.6",
"description": "Official Codex plugin bundle for Legion's multi-agent planning, execution, review, and shipping workflows.",
"author": {
"name": "9thLevelSoftware",
"url": "https://github.com/9thLevelSoftware"
},
"homepage": "https://9thlevelsoftware.github.io/legion/",
"repository": "https://github.com/9thLevelSoftware/legion",
"license": "MIT",
"keywords": [
"legion",
"codex",
"plugin",
"multi-agent",
"workflow-orchestration",
"project-management"
],
"skills": "./skills/",
"interface": {
"displayName": "Legion",
"shortDescription": "Multi-agent project orchestration for Codex.",
"longDescription": "Legion packages guided planning, phase execution, QA review, shipping, and portfolio workflows for Codex. It exposes the Legion skill set directly from this repository without changing the existing npm installer flow.",
"developerName": "9thLevelSoftware",
"category": "Productivity",
"capabilities": [
"Interactive",
"Write"
],
"websiteURL": "https://9thlevelsoftware.github.io/legion/",
"defaultPrompt": [
"Use Legion to start a new project and capture the roadmap.",
"Use Legion to plan the next phase and recommend the right agents.",
"Use Legion to review the current phase and route any fixes."
],
"brandColor": "#0F766E"
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[legion on Agent Plugins Marketplace](https://pluginsmp.com/plugins/legion-2)