Agent Plugins Marketplace
← All plugins

instructions

v0.18.1

Create and audit instruction assets: skills, subagents, and agent prompt standards

CodexClaude Code7 Skills

By Simon HeimlicherLicense: MIT1 GitHub starsUpdated last week

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
7 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 instructions for Codex and Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install instructions-3@agent-plugin-marketplace

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

Compatibility: the page URL and API slug “instructions-3” remain stable.

  • Codex: Legacy selector instructions-3@agent-plugin-marketplace remains documented for migration; install from source for this runtime.

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.

Codex has another source with the same manifest name. This directory does not invent numbered install aliases; use the publisher's catalog or inspect the source manually for that runtime.

Get the source manually
git clone https://github.com/outcomeeng/plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is src/plugins/instructions/.

Plugin files

src/plugins/instructions/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/agent-prompt-standards/SKILL.md
├── skills/audit-skill/SKILL.md
├── skills/audit-subagent/SKILL.md
├── skills/create-skill/SKILL.md
├── skills/create-subagent/SKILL.md
├── skills/skill-standards/SKILL.md
└── skills/subagent-standards/SKILL.md

Included Skills7

agent-prompt-standardsskills/agent-prompt-standards/SKILL.md

Agent prompt writing conventions enforced across all creator and auditor skills. Loaded by other skills, not invoked directly.

audit-skillskills/audit-skill/SKILL.md

SKILL.md audit methodology — judges skill content for standards compliance, operational effectiveness, portability, voice, and structure.

audit-subagentskills/audit-subagent/SKILL.md

{{! term('configured_agent') | capitalize !}}-configuration audit methodology — judges a {{! term('configured_agent') !}} configuration file against the subagent and agent-prompt standards, covering frontmatter, role framing, constraints, and output contract.

create-skillskills/create-skill/SKILL.md

ALWAYS invoke this skill when creating, editing, or improving SKILL.md files or bundled workflows, references, templates, and scripts; explaining skill patterns; or verifying that skill content is current.

create-subagentskills/create-subagent/SKILL.md

ALWAYS invoke this skill when creating, editing, or configuring {{! term('configured_agents') !}}. NEVER create {{! term('configured_agents') !}} without this skill.

skill-standardsskills/skill-standards/SKILL.md

Skill authoring standards enforced across all creating and auditing skills. Loaded by other skills, not invoked directly.

subagent-standardsskills/subagent-standards/SKILL.md

Configuration, profile, authority, context-isolation, and output-contract standards for configured subagents. Loaded by creator and auditor skills.

Plugin manifests2

src/plugins/instructions/.codex-plugin/plugin.json
{
  "name": "instructions",
  "version": "0.18.1",
  "description": "Create and audit instruction assets: skills, subagents, and agent prompt standards",
  "author": {
    "name": "Simon Heimlicher",
    "url": "https://github.com/outcomeeng"
  },
  "homepage": "https://github.com/outcomeeng/plugins",
  "repository": "https://github.com/outcomeeng/plugins",
  "license": "MIT",
  "keywords": [
    "development",
    "plugin",
    "marketplace",
    "skill",
    "agent",
    "subagent",
    "prompt",
    "codex",
    "claude code"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Instruction Authoring",
    "shortDescription": "Create and audit instruction assets",
    "longDescription": "Create and audit skills, subagents, and agent prompt standards for Codex and Claude Code workflows.",
    "developerName": "Outcome Engineering",
    "category": "Developer Tools",
    "capabilities": [
      "Read",
      "Write"
    ],
    "websiteURL": "https://outcome.engineering"
  }
}
src/plugins/instructions/.claude-plugin/plugin.json
{
  "name": "instructions",
  "version": "0.18.1",
  "description": "Create and audit instruction assets: skills, subagents, and agent prompt standards",
  "author": {
    "name": "Simon Heimlicher"
  },
  "repository": "https://github.com/outcomeeng/plugins",
  "license": "MIT",
  "keywords": [
    "development",
    "plugin",
    "marketplace",
    "skill",
    "agent",
    "subagent",
    "prompt",
    "codex",
    "claude code"
  ]
}

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.

[instructions on Agent Plugins Marketplace](https://pluginsmp.com/plugins/instructions-3)