agent-architecture-review-sample AGENTS.md

agent-architecture-review-sample AGENTS.md is an instructions file for Codex, OpenCode from Azure-Samples/agent-architecture-review-sample. It costs 2,975 tokens per session, scanned A, original, MIT.

Repository instructions for an AI architecture-review application that examines software descriptions and produces risk assessments, diagrams, image exports, and recommendations.

In plain words
What is it for?
Use them when working on the application’s hosted agent, web API, parsing and risk-detection logic, diagram rendering, local runner, or deployment files.
Why use it?
They help coding agents understand the repository’s purpose, file responsibilities, and how its input flows through the system.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/azure-samples/agent-architecture-review-sample/agents-md
Clone the repo
git clone --depth 1 https://github.com/Azure-Samples/agent-architecture-review-sample

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for agent-architecture-review-sample AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/azure-samples/agent-architecture-review-sample/agents-md.svg)](https://agentmods.dev/instructions/azure-samples/agent-architecture-review-sample/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/azure-samples/agent-architecture-review-sample/agents-md"><img src="https://agentmods.dev/badge/instructions/azure-samples/agent-architecture-review-sample/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,975 This file is loaded in full into every session.
When invoked 2,975 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02975 $0.02975
Opus 5 $0.01488 $0.01488
Sonnet 5 $0.00595 $0.00595
Haiku 4.5 $0.00298 $0.00298

Measured 6d ago against content hash c6aa06171556, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent-architecture-review-sample 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 6d 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.

AGENTS.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents Guide — Architecture Review Agent Sample

This file helps AI coding agents (GitHub Copilot, Copilot Workspace, Codespaces agents, etc.) understand and work effectively with this repository.


Repository Purpose

This is an AI-powered Architecture Review Agent that analyses software architecture descriptions and generates interactive diagrams. It accepts any input format (YAML, Markdown, plaintext, code, design docs, prose) and returns structured risk assessments, Excalidraw diagrams, PNG exports, and actionable recommendations.


Project Structure

agent-architecture-review-sample/
├── main.py              # Hosted agent entry point (Microsoft Agent Framework / Foundry)
├── api.py               # FastAPI backend (REST API for the web UI)
├── tools.py             # Core engine — all tool logic (parser, risk detector, diagram renderer, MCP client, PNG export)
├── run_local.py         # CLI runner for local testing (no Azure required for structured inputs)
├── agent.yaml           # Foundry hosted agent deployment manifest
├── requirements.txt     # Python dependencies (pinned versions)
├── pyproject.toml       # Pytest configuration
├── Dockerfile           # Container for hosted agent deployment
├── Dockerfile.web       # Container for web app deployment (FastAPI + React)
├── docs/deployment.md   # Step-by-step deployment & RBAC guide
├── frontend/            # React UI (Vite + Excalidraw)
│   ├── src/App.jsx      # Main React app with input, tabs, results
│   ├── src/api.js       # API client — calls FastAPI backend
│   └── src/components/  # Summary, RiskTable, ComponentMap, DiagramViewer, Recommendations
├── scenarios/           # Pre-built demo architecture files (YAML, Markdown)
├── tests/               # Pytest test suite
│   ├── conftest.py      # Shared fixtures (sample components, connections)
│   ├── test_tools.py    # Unit tests for tools.py functions
│   ├── test_api.py      # FastAPI endpoint tests
│   └── test_integration.py  # Integration tests
├── scripts/             # Automation scripts
│   ├── windows/         # PowerShell: setup.ps1, dev.ps1, deploy-webapp.ps1, teardown.ps1
│   └── linux-mac/       # Bash: setup.sh, dev.sh, deploy-webapp.sh, teardown.sh
└── output/              # Generated outputs (auto-created): .excalidraw, .png, .json

Read the full file on GitHub · 272 lines

Changes

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.

  1. 6d ago First seen · 272 lines · 2,975 tokens per session scan A c6aa06171556

Subscribe to this mod's changes

agent-architecture-review-sample AGENTS.md is an instructions file published in the GitHub repository Azure-Samples/agent-architecture-review-sample (98 stars, last pushed 2mo ago), licensed MIT. It adds 2,975 tokens to every session, about $0.0149 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.