---
id: "/agents/advanced/"
title: "Agents and harnesses for advanced learners"
creator: null
url: "https://skillissue.dev/agents/advanced/"
level: null
category: null
models: null
source_date: null
date_added: null
---

# Agents and harnesses for advanced learners

[Beginner](/agents/beginner/index.md) [Intermediate](/agents/intermediate/index.md) [Advanced](/agents/advanced/index.md) [Expert](/agents/expert/index.md)

10 resources

- 

### [Effective harnesses for long-running agents](/e/anthropic-effective-harnesses-long-running-agents/index.md)

by [Anthropic](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents)

Harness design for agents that work across many context windows.

Advanced · claude · 2025-11-26

- 

### [How we built our multi-agent research system](/e/anthropic-multi-agent-research-system/index.md)

by [Anthropic](https://www.anthropic.com/engineering/multi-agent-research-system)

Real production lessons on orchestrator/sub-agent design and its costs.

Advanced · claude · 2025-06-13

- 

### [Writing effective tools for AI agents](/e/anthropic-writing-tools-for-agents/index.md)

by [Anthropic](https://www.anthropic.com/engineering/writing-tools-for-agents)

How to design, evaluate and improve the tools an agent calls.

Advanced · any · 2025-09-11

- 

### [Context Rot: How Increasing Input Tokens Impacts LLM Performance](/e/chroma-context-rot/index.md)

by [Chroma](https://www.trychroma.com/research/context-rot)

Measures how output quality drops as input length grows.

Advanced · any · date not stated

- 

### [Don't Build Multi-Agents](/e/cognition-dont-build-multi-agents/index.md)

by [Cognition](https://cognition.com/blog/dont-build-multi-agents)

The counter-argument: context sharing beats splitting work across agents.

Advanced · any · 2025-06-12

- 

### [Context Engineering for AI Agents: Lessons from Building Manus](/e/manus-context-engineering-lessons/index.md)

by [Manus](https://manus.im/blog/Context-Engineering-for-AI-Agents-Lessons-from-Building-Manus)

KV-cache-aware design, file system as memory, keep errors in context.

Advanced · any · date not stated

- 

### [MCP reference servers](/e/mcp-reference-servers/index.md)

by [MCP project](https://github.com/modelcontextprotocol/servers)

Reference implementations to learn MCP server design from.

Advanced · any · date not stated

- 

### [OpenHands](/e/openhands-openhands/index.md)

by [OpenHands (All Hands AI)](https://github.com/OpenHands/OpenHands)

Open-source coding-agent platform worth reading as a reference harness.

Advanced · any · date not stated

- 

### [The lethal trifecta for AI agents](/e/willison-lethal-trifecta/index.md)

by [Simon Willison](https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/)

A defensive framework for recognizing risky combinations of agent capabilities and untrusted inputs.

Advanced · any · 2025-06-16

- 

### [Design Patterns for Securing LLM Agents against Prompt Injections](/e/willison-prompt-injection-design-patterns/index.md)

by [Simon Willison](https://simonwillison.net/2025/Jun/13/prompt-injection-design-patterns/)

Summary of a paper's defensive agent architectures.

Advanced · any · 2025-06-13