agent-patterns

Architecture guidance for building TypeAgent agents, which are software agents that handle specific kinds of requests. It defines a shared interface and describes nine patterns for communicating with services, storing state, and producing results.

In plain words
What is it for?
Use it to design new TypeAgent agents, select scaffolding patterns, understand dispatcher integration, and decide how an agent should connect to external systems.
Why use it?
It helps developers choose a suitable structure before implementing an agent. This reduces uncertainty about whether an agent should use an API, stream language-model output, orchestrate sub-agents, or use another pattern.

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/microsoft/typeagent/agent-patterns
Clone the repo
git clone --depth 1 https://github.com/microsoft/TypeAgent
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,700 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.02700
Opus 5 $0.00000 $0.01350
Sonnet 5 $0.00000 $0.00540
Haiku 4.5 $0.00000 $0.00270

Measured yesterday against content hash cc20ddddc931, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-patterns scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

Invokes platform APIs directly via `child_process.exec` / `spawn`, device
ts/docs/architecture/agents/agent-patterns.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Patterns — Architecture & Design

Scope: This document describes the nine architectural patterns used by TypeAgent application agents. Use it when designing a new agent or choosing a scaffolding template. For the dispatcher that hosts agents, see dispatcher.md. For how to automate agent creation, see the onboarding agent at packages/agents/onboarding/.

Overview

Every TypeAgent agent exports an instantiate(): AppAgent function and implements the AppAgent interface from @typeagent/agent-sdk. Beyond that common contract, agents fall into nine patterns based on how they communicate with external systems, whether they manage persistent state, and what kind of output they produce.

Pattern When to use Examples
schema-grammar Bounded set of typed actions (default) weather, photo, list
external-api Authenticated REST / cloud API calendar, email, player
llm-streaming Agent calls an LLM, streams results chat, greeting
sub-agent-orchestrator API surface too large for one schema desktop, code, browser
websocket-bridge Automate a host app via a plugin browser, code
state-machine Multi-phase workflow with approval gates onboarding, powershell
native-platform OS / device APIs, no cloud playerLocal, desktop
view-ui Rich interactive web-view UI turtle, montage, markdown
command-handler Simple settings-style direct dispatch settings, test

Pattern details

1. schema-grammar — Standard (default)

The canonical TypeAgent pattern. Define TypeScript action types, generate a .agr grammar file for natural language matching, and implement a typed dispatch handler.

Read the full file on GitHub · 356 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 · 356 lines · 0 tokens per session scan A cc20ddddc931

Subscribe to this mod's changes

agent-patterns is an agent published in the GitHub repository microsoft/TypeAgent (738 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,700 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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