Agent Plugins Marketplace
← All plugins

agent-rules

v0.2.17

Visible, bounded behavioral corrections with Jev and editable policies.

CodexClaude Code2 Skills

By Jamie SteinerLicense: MIT0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
2 skill or MCP entries
Source updated
Sep 27, 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 agent-rules for Codex and Claude Code

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

Paste 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 “agent-rules-2” remain stable.

  • Codex: agent-rules-2@agent-plugin-marketplace → agent-rules@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/jvsteiner/agent-rules

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

agent-rules/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/author-rule/SKILL.md
└── skills/diagnose-rule/SKILL.md

Included Skills2

author-ruleskills/author-rule/SKILL.md

Create, validate, calibrate, and enable Agent Rules policies from a user's concrete behavioral preference. Use when the user asks to add or refine a behavior rule; do not use for ordinary code checks or generic policy writing.

diagnose-ruleskills/diagnose-rule/SKILL.md

Explain why an Agent Rules policy fired, abstained, or failed to correct, using recorded session judgments and outcomes. Use when debugging a rule or investigating a plugin notice.

Plugin manifests2

.codex-plugin/plugin.json
{
  "name": "agent-rules",
  "version": "0.2.17",
  "description": "Visible, bounded behavioral corrections with Jev and editable policies.",
  "author": {
    "name": "Jamie Steiner"
  },
  "license": "MIT",
  "hooks": "./hooks/codex.json",
  "skills": "./skills/",
  "interface": {
    "displayName": "Agent Rules",
    "shortDescription": "Inspect and correct undesirable agent behavior.",
    "longDescription": "Editable policies, Jev classification, and bounded corrective feedback for coding agents.",
    "developerName": "Jamie Steiner",
    "category": "Productivity",
    "capabilities": [
      "Read",
      "Write"
    ],
    "defaultPrompt": [
      "Help me author a behavioral rule and evaluate it against examples."
    ]
  }
}
.claude-plugin/plugin.json
{
  "name": "agent-rules",
  "version": "0.2.17",
  "description": "Visible, bounded behavioral corrections with Jev and editable policies.",
  "author": {
    "name": "Jamie Steiner"
  },
  "license": "MIT",
  "hooks": "./hooks/claude.json"
}

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.

[agent-rules on Agent Plugins Marketplace](https://pluginsmp.com/plugins/agent-rules-2)