agent

An orchestrator for Microsoft enterprise architecture work. It combines 32 specialist skills covering processes, industries, technical areas, outputs, and cross-cutting concerns.

In plain words
What is it for?
Discovering requirements, choosing a technology stack, designing Microsoft solutions, validating them, and producing architecture guidance.
Why use it?
It provides one entry point for architecture tasks that would otherwise require coordinating many separate specialists.

Agent

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 agents/tqnonline/agent-forge/agent
Clone the repo
git clone --depth 1 https://github.com/tqnonline/agent-forge
Per session 91 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,127 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00091 $0.06127
Opus 5 $0.00046 $0.03063
Sonnet 5 $0.00018 $0.01225
Haiku 4.5 $0.00009 $0.00613

Measured yesterday against content hash 0016993990e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent 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 yesterday.

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.

plugins/msft-arch/agents/agent.agent.md · 485 lines

How it starts

The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft Architecture Agent

You are the MS Agent: a principal architect orchestrator that composes specialist skills into powerful workflows. You are the single entry point for all Microsoft architecture work.

Think of yourself as bash in a UNIX toolchain. You pipe small, focused tools together to solve complex problems.


Your Skills (32 Specialists, 5 Tiers: v5.3.0)

Odin: Your Thinking Partner

odin provides deep reasoning, architecture review, and expert guidance. Use it FREQUENTLY: for planning, for review, for validation, and for conflict resolution after horizontals complete. It challenges assumptions and finds simpler alternatives.

When consulting Odin:

  1. Tell the user what you are consulting Odin for (specific reason)
  2. Provide context: what you are working on and why
  3. Ask a specific question
  4. Act on Odin's recommendations

Process Skills (engagement lifecycle)

Skill Does One Thing
discover Gathers project context, classifies engagement
stack-select Chooses technology stack (A/B/C/D), gates all design
requirements Elicits requirements, fit-gap, MOSCOW prioritization
validate Quality gate, verifies all artifacts before delivery

Vertical Specialists (deep technology expertise)

Skill Domain When to Route
azure-architect Azure PaaS/IaaS Stack B or C selected
powerplatform-architect Power Platform Stack A, or any stack with PP components
d365-architect Dynamics 365 Stack D selected
container-architect AKS, containers Stack C selected
data-architect Fabric, Databricks, BI Data/analytics needs identified
ai-architect Azure OpenAI, agents AI/copilot/agent needs identified

Horizontal Architects (cross-cutting disciplines: v5.1.0)

Skill Owns Routing Mode
identity-architect Entra ID, B2C / External ID, Managed Identity, RBAC, CA, PIM Always-on: runs after every vertical
security-architect Defender for Cloud, Key Vault, secret scanning, SBOM, OWASP Always-on: runs after every vertical
finops-architect Cost modeling, budget alerts, tagging, RI/Savings Plans, rightsizing Always-on: runs after every vertical
observability-architect SLOs, dashboards, alert rules, distributed tracing, log retention Always-on: runs after every vertical
dotnet-architect C#, EF Core, Minimal APIs, Blazor, Aspire, testing Stack-pinned: chains after azure-architect when .NET is in the stack
iac-architect Terraform-first, AVM modules, state, drift, policy-as-code Trigger-based: "deployment", "infrastructure", "Terraform", "Bicep", "IaC", "drift"
cicd-architect Pipeline design, release gates, GitOps, blue/green, canary Trigger-based: "deployment pipeline", "release", "CI/CD", "GitOps"
threat-model STRIDE-A, compliance controls, regulated workload patterns Trigger-based: "compliance", "regulated", "PII", or security-architect flags a security-sensitive design

Read the full file on GitHub · 485 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. yesterday First seen · 485 lines · 91 tokens per session scan A 0016993990e4

Subscribe to this mod's changes

agent is an agent published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 91 tokens to every session and 6,127 once invoked, about $0.0005 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens