agent-sop: Instructions file for Codex

AGENTS.md - AI Assistant Context for Agent SOP Project

Project Overview

Agent SOP provides natural language workflows that enable AI agents to perform complex, multi-step tasks with consistency and reliability. This is a Python package that implements the Model Context Protocol (MCP) for AI assistant integration and supports conversion to Agent Skills format.

Directory Structure

agent-sop/
├── python/strands_agents_sops/    # Main Python package
│   ├── __main__.py               # CLI entry point (mcp|skills|rule commands)
│   ├── mcp.py                    # MCP server implementation
│   ├── skills.py                 # Agent Skills conversion
│   └── utils.py                  # Shared SOP utilities
├── agent-sops/                   # Source SOP definitions
│   ├── codebase-summary.sop.md   # Documentation generation workflow
│   ├── code-assist.sop.md        # TDD implementation workflow
│   ├── code-task-generator.sop.md # Task breakdown workflow
│   └── pdd.sop.md               # Prompt-driven development workflow
├── python/tests/                 # Comprehensive test suite
├── spec/                         # SOP format specification
└── rules/                        # SOP authoring guidelines

Development Patterns

SOP Format Structure

All SOPs follow this standardized format:

# SOP Title

## Overview
Brief description of what this SOP accomplishes and when to use it.

## Parameters
- **required_param** (required): Description of required input
- **optional_param** (optional, default: value): Description with default

## Steps
### 1. Step Name
Description of what this step accomplishes.

**Constraints:**
- You MUST perform required actions
- You SHOULD follow recommended practices
- You MAY include optional enhancements
- You MUST NOT perform prohibited actions

## Examples
Concrete usage examples showing input and expected outcomes.

## Troubleshooting
Common issues and their solutions.

RFC 2119 Constraint Keywords

• MUST: Required actions that cannot be skipped
• MUST NOT: Prohibited behaviors, forbidden actions
• SHOULD: Recommended practices for optimal results
• SHOULD NOT: Not recommended, but not forbidden
• MAY: Optional enhancements or alternatives