Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/strands-agents/agent-sop/agents-mdgit clone --depth 1 https://github.com/strands-agents/agent-sopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/strands-agents/agent-sop/agents-md)<a href="https://agentmods.dev/instructions/strands-agents/agent-sop/agents-md"><img src="https://agentmods.dev/badge/instructions/strands-agents/agent-sop/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02083 | $0.02083 |
| Opus 5 | $0.01042 | $0.01042 |
| Sonnet 5 | $0.00417 | $0.00417 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
agent-sop AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 267 lines · 2,083 tokens per session scan A b3ec388fb088
agent-sop AGENTS.md is an instructions file published in the GitHub repository strands-agents/agent-sop (1,141 stars, last pushed 27d ago), licensed Apache-2.0. It adds 2,083 tokens to every session, about $0.0104 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
robots AGENTS.md
AGENTS.md instructions for strands-labs/robots, covering agents.md - strands-labs/robots, project dashboard, repository structure, development and install with all optional deps.
strands-sglang AGENTS.md
Instructions for strands-rl/strands-sglang, covering agents.md, project overview, commands, setup and linting.
job-search-agent AGENTS.md
Instructions for deeheber/job-search-agent, covering job search agent and conventions.
sdk-python AGENTS.md
Instructions for strands-compose/sdk-python, covering strands-compose — agent instructions, response style, do not, still required and read the skill first — mandatory.
devduck AGENTS.md
Instructions for cagataycali/devduck, covering agents.md — devduck, project: devduck, architecture, key design patterns and self-awareness.
sample-agentic-chatbot-accelerator CLAUDE.md
Claude Code instructions for aws-samples/sample-agentic-chatbot-accelerator, covering claude.md, project, common commands, cdk (default) and terraform (experimental).