Agent Plugins Marketplace
← All plugins

codex-workflow-governor

v0.13.5

Orchestrate parallel Codex agents with reusable DAG workflows, strict outputs, detached runs, adaptive research, and persistent loops

Codex4 Skills1 MCP serverstdio

By BearsCLOUDLicense: MIT0 GitHub starsUpdated 2 hours ago

Directory evidence

Runtimes
Codex
Parsed components
5 skill or MCP entries
Source updated
Aug 24, 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 plugin

Installs for the current user
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add codex-workflow-governor@agent-plugin-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.

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/BearsCLOUD/codex-workflow-governor

Clone 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-workflow-governor/
├── .codex-plugin/plugin.json
├── skills/adaptive-deepening/SKILL.md
├── skills/codex-workflows/SKILL.md
├── skills/graph-completion/SKILL.md
├── skills/score-documentation-quality/SKILL.md
└── .mcp.json

Included Skills4

adaptive-deepeningskills/adaptive-deepening/SKILL.md

Deepen research, decision support, or synthesis through evidence-driven waves selected from the current gap map. Use when an upfront plan cannot expose every important question.

codex-workflowsskills/codex-workflows/SKILL.md

Run, monitor, and author reviewed finite, prompt-compiled, or persistent Codex task graphs with bounded fan-out, strict outputs, checkpoints, and project or builtin workflow authority. Use for parallel workers, dependency graphs, detached runs, adaptive waves, or durable monitors; use direct codex exec for one isolated task.

graph-completionskills/graph-completion/SKILL.md

Complete decision-relevant knowledge graph gaps with source-linked candidate facts, validation, conflict handling, and explicit stopping rules. Use for research, planning, and synthesis over entities and relations.

score-documentation-qualityskills/score-documentation-quality/SKILL.md

Assess or improve Markdown documentation and instruction hierarchies with a quick edit, evidence-backed score, topology check, or isolated draft optimization. Use formal scoring only when the user asks for a score, audit, comparison, or quality gate; use graph/topology analysis only for real ownership or precedence ambiguity.

MCP servers1

workflow-governor-localstdio
command
python3
args
./mcp/server.py
cwd
.

Plugin manifests1

.codex-plugin/plugin.json
{
  "name": "codex-workflow-governor",
  "version": "0.13.5",
  "description": "Orchestrate parallel Codex agents with reusable DAG workflows, strict outputs, detached runs, adaptive research, and persistent loops",
  "author": {
    "name": "BearsCLOUD",
    "url": "https://github.com/BearsCLOUD"
  },
  "homepage": "https://github.com/BearsCLOUD/codex-workflow-governor",
  "repository": "https://github.com/BearsCLOUD/codex-workflow-governor",
  "license": "MIT",
  "keywords": [
    "codex",
    "codex-cli",
    "codex-plugin",
    "workflow",
    "workflow-automation",
    "multi-agent",
    "agent-orchestration",
    "parallel-agents",
    "dag",
    "async",
    "background-tasks",
    "persistent-loops",
    "mcp",
    "structured-output",
    "governance",
    "documentation",
    "instructions"
  ],
  "skills": "./skills/",
  "mcpServers": "./.mcp.json",
  "interface": {
    "displayName": "Codex Workflow Governor",
    "shortDescription": "Orchestrate parallel Codex agents in durable task graphs.",
    "longDescription": "Build and run reusable Codex multi-agent workflows: parallel DAG tasks, strict structured outputs, detached execution, adaptive research waves, persistent loops, checkpoints, monitoring, and restart-safe persisted results.",
    "developerName": "BearsCLOUD",
    "category": "Developer Tools",
    "capabilities": [
      "Interactive",
      "Write"
    ],
    "defaultPrompt": [
      "Run a parallel multi-agent analysis and synthesize the results into one validated JSON output.",
      "Compile a bounded adaptive research workflow that deepens only when evidence gaps justify another wave.",
      "Start a persistent Codex monitoring loop with checkpoints, backoff, and explicit pause or cancellation controls."
    ]
  }
}

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.

[codex-workflow-governor on Agent Plugins Marketplace](https://pluginsmp.com/plugins/codex-workflow-governor)