# AI Agents — MDRSS semantic catalog

> Semantic domain: ai-agents
> Coding agents, agent frameworks, tools, prompting, evaluation, safety, and autonomous workflows.
> Aggregate catalog URL: https://mdrss.com/catalog/ai-agents?page=2

## Feeds

- [AI, Agents & Prompting](https://mdrss.com/s/ai-agents-and-prompting) — Agent frameworks, model behavior, evaluation, prompting, and MCP.
- [AI Search, GEO & SEO](https://mdrss.com/s/ai-search-geo-and-seo) — AI visibility, answer-engine optimization, structured data, and search quality.

## Aggregate endpoints

- RSS: https://mdrss.com/catalog/ai-agents/rss.xml?page=2
- JSON: https://mdrss.com/catalog/ai-agents/feed.json?page=2

## Semantic domain cards (224)

### [Agent Performance Optimization Workflow](https://mdrss.com/ai-agents/agent-design-and-orchestration/901185/901185.md)

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration. Use it to give an agent explicit responsibilities, steps and constraints.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:20.577Z · Version: 1

### [Usage Guide](https://mdrss.com/ai-agents/agent-design-and-orchestration/901181/901181.md)

Complete guide to using agents, slash commands, and multi-agent workflows. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:20.577Z · Version: 1

### [PluginEval: Quality Evaluation Framework](https://mdrss.com/ai-agents/agent-design-and-orchestration/901179/901179.md)

PluginEval is a three-layer quality evaluation framework for Claude Code plugins and skills. It combines deterministic static analysis, LLM-based semantic judging, and Monte Carlo simulation to produce calibrated quality scores with confidence intervals. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:18.640Z · Version: 1

### [Cross-harness capability matrix](https://mdrss.com/ai-agents/agent-design-and-orchestration/901178/901178.md)

claude-agents is a multi-harness plugin marketplace. Source-of-truth lives under plugins/ as Claude Code markdown. Per-harness artifacts are generated by adapters under tools/adapters/. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:18.640Z · Version: 1

### [Authoring portable plugin content](https://mdrss.com/ai-agents/agent-design-and-orchestration/901177/901177.md)

Plugin content in this repo ships to five harnesses: OpenAI Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot. Claude Code is the source-of-truth. The adapter framework handles per-harness mechanics (frontmatter rewrites, format transforms, output paths) so you auth. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:18.640Z · Version: 1

### [Architecture & Design Principles](https://mdrss.com/ai-agents/agent-design-and-orchestration/901176/901176.md)

This marketplace follows industry best practices with a focus on granularity, composability, and minimal token usage. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:18.640Z · Version: 1

### [Agent Reference](https://mdrss.com/ai-agents/agent-design-and-orchestration/901175/901175.md)

Complete reference for all 203 local specialized AI agents organized by category with model assignments. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:18.640Z · Version: 1

### [Architecture](https://mdrss.com/ai-agents/agent-design-and-orchestration/901173/901173.md)

Top-level architectural map for the claude-agents marketplace. Detail lives in docs/architecture.md; this file is the index per the OpenAI harness-engineering pattern. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:18.640Z · Version: 1

### [Python MCP Server Implementation Guide](https://mdrss.com/ai-agents/mcp-tooling-and-context/901162/901162.md)

This document provides Python-specific best practices and examples for implementing MCP servers using the MCP Python SDK. It covers server setup, tool registration patterns, input validation with Pydantic, error handling, and complete working examples. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:18.640Z · Version: 1

### [Node/TypeScript MCP Server Implementation Guide](https://mdrss.com/ai-agents/mcp-tooling-and-context/901161/901161.md)

This document provides Node/TypeScript-specific best practices and examples for implementing MCP servers using the MCP TypeScript SDK. It covers project structure, server setup, tool registration patterns, input validation with Zod, error handling, and complete working examples. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:18.640Z · Version: 1

### [MCP Server Best Practices](https://mdrss.com/ai-agents/mcp-tooling-and-context/901160/901160.md)

The name should be general, descriptive of the service being integrated, easy to infer from the task description, and without version numbers. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:18.640Z · Version: 1

### [MCP Server Evaluation Guide](https://mdrss.com/ai-agents/mcp-tooling-and-context/901159/901159.md)

This document provides guidance on creating comprehensive evaluations for MCP servers. Evaluations test whether LLMs can effectively use your MCP server to answer realistic, complex questions using only the tools provided. Use it to navigate the topic and choose relevant methods, papers or tools.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:18.640Z · Version: 1

### [MCP Server Development Guide](https://mdrss.com/ai-agents/mcp-tooling-and-context/901158/901158.md)

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks. Use it to make implementation decisions and avoid common dead ends.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:18.640Z · Version: 1

### [Managed Agents — TypeScript](https://mdrss.com/ai-agents/agent-design-and-orchestration/901155/901155.md)

List files the agent wrote to /mnt/session/outputs/ during a session, then. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:18.640Z · Version: 1

### [Tool Use — TypeScript](https://mdrss.com/ai-agents/agent-design-and-orchestration/901154/901154.md)

For conceptual overview (tool definitions, tool choice, tips), see shared/tool-use-concepts.md. Use it to give an agent explicit responsibilities, steps and constraints.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Claude API — TypeScript](https://mdrss.com/ai-agents/agent-design-and-orchestration/901153/901153.md)

For operator instructions that arrive mid-conversation (mode switches, injected state), append {role: "system", ..} to messages instead of editing top-level system — this preserves the cached prefix and carries operator authority. Must follow a user message (or an assista. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Tool Use Concepts](https://mdrss.com/ai-agents/agent-design-and-orchestration/901152/901152.md)

This file covers the conceptual foundations of tool use with the Claude API. For language-specific code examples, see the python/, typescript/, or other language folders. For decision heuristics on which tools to expose, how to manage context in long-running agents, and cachi. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Prompt Caching — Design & Optimization](https://mdrss.com/ai-agents/agent-design-and-orchestration/901151/901151.md)

This file covers how to design prompt-building code for effective caching. For language-specific syntax, see the Prompt Caching section in each language's README or single-file doc. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Model Migration Guide](https://mdrss.com/ai-agents/agent-design-and-orchestration/901150/901150.md)

How to move existing code to newer Claude models. Covers breaking changes, deprecated parameters, and drop-in replacements for retired models. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Webhooks](https://mdrss.com/ai-agents/agent-design-and-orchestration/901149/901149.md)

Anthropic can POST to your HTTPS endpoint when a Managed Agents resource changes state — an alternative to holding an SSE stream or polling. Payloads are thin (event type + resource IDs only); on receipt, fetch the resource for current state. Every delivery is HMAC-signed. Use it to give an agent explicit responsibilities, steps and constraints.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Tools & Skills](https://mdrss.com/ai-agents/agent-design-and-orchestration/901148/901148.md)

Override defaults for individual tools. This example enables everything except bash:. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Self-Hosted Sandboxes](https://mdrss.com/ai-agents/agent-design-and-orchestration/901147/901147.md)

With config.type: "self hosted", the agent loop stays on Anthropic's orchestration layer but tool execution moves to infrastructure you control — bash, file ops, and code run inside your container, so filesystem contents and network egress never leave your environment. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Scheduled Deployments](https://mdrss.com/ai-agents/agent-design-and-orchestration/901146/901146.md)

A scheduled deployment runs an agent on a recurring cron schedule — each firing creates a session autonomously. Use it for predictable-cadence work: nightly triage, weekly compliance scans, hourly monitors. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Overview](https://mdrss.com/ai-agents/agent-design-and-orchestration/901145/901145.md)

Managed Agents provisions a container per session as the agent's workspace. The agent loop runs on Anthropic's orchestration layer; the container is where the agent's tools execute — bash commands, file operations, code. You create a persisted Agent config (model, system pr. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Outcomes](https://mdrss.com/ai-agents/agent-design-and-orchestration/901144/901144.md)

An outcome elevates a session from conversation to work : you state what "done" looks like, and the harness runs an iterate → grade → revise loop until the artifact meets the rubric, hits max iterations, or is interrupted. A separate grader (independent context windo. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Onboarding Flow](https://mdrss.com/ai-agents/agent-design-and-orchestration/901143/901143.md)

Claude Managed Agents is a hosted agent: Anthropic runs the agent loop and provisions a sandboxed container per session where the agent's tools execute (or your own worker, with a self hosted environment — see shared/managed-agents-self-hosted-sandboxes.md). You supply an a. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Multiagent Sessions](https://mdrss.com/ai-agents/agent-design-and-orchestration/901142/901142.md)

A coordinator agent can delegate to other agents within one session. All agents share the container and filesystem ; each runs in its own thread — a context-isolated event stream with its own conversation history, model, system prompt, tools, MCP servers, and skills (from. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Memory Stores](https://mdrss.com/ai-agents/agent-design-and-orchestration/901141/901141.md)

Sessions are ephemeral by default — when one ends, anything the agent learned is gone. A memory store is a workspace-scoped collection of small text documents that persists across sessions. When a store is attached to a session (via resources ), it is mounted into the cont. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Events & Steering](https://mdrss.com/ai-agents/agent-design-and-orchestration/901140/901140.md)

Send events to a session via POST /v1/sessions/{id}/events. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Environments & Resources](https://mdrss.com/ai-agents/agent-design-and-orchestration/901139/901139.md)

Creating a session requires an environment id. Environments are reusable configuration templates for spinning up containers in Anthropic's infrastructure — you might create different environments for different use cases (e.g. data visualization vs web development, with diff. Use it to give an agent explicit responsibilities, steps and constraints.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Core Concepts](https://mdrss.com/ai-agents/agent-design-and-orchestration/901138/901138.md)

Every session has a live trace view in the Anthropic Console at https://platform.claude.com/workspaces/{workspace}/sessions/{session id}. Print this URL immediately after creating a session so the user can watch tool calls and messages stream in real time. {workspace} is th. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Common Client Patterns](https://mdrss.com/ai-agents/agent-design-and-orchestration/901137/901137.md)

Patterns you'll write on the client side when driving a Managed Agent session, grounded in working SDK examples. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Endpoint Reference](https://mdrss.com/ai-agents/agent-design-and-orchestration/901136/901136.md)

All endpoints require x-api-key and anthropic-version: 2023-06-01 headers. Managed Agents endpoints additionally require the anthropic-beta header. Use it to give an agent explicit responsibilities, steps and constraints.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Live Documentation Sources](https://mdrss.com/ai-agents/agent-design-and-orchestration/901135/901135.md)

This file contains WebFetch URLs for fetching current information from platform.claude.com and Agent SDK repositories. Use these when users need the latest data that may have changed since the cached content was last updated. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [HTTP Error Codes Reference](https://mdrss.com/ai-agents/agent-design-and-orchestration/901134/901134.md)

This file documents HTTP error codes returned by the Claude API, their common causes, and how to handle them. For language-specific error handling examples, see the python/ or typescript/ folders. Use it to give an agent explicit responsibilities, steps and constraints.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Anthropic CLI (ant)](https://mdrss.com/ai-agents/agent-design-and-orchestration/901133/901133.md)

The ant CLI exposes every Claude API resource as a shell subcommand. Compared to curl: request bodies are built from typed flags or piped YAML instead of hand-written JSON, @path inlines file contents into any string field, --transform extracts fields with a GJSON path (n. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Agent Design Patterns](https://mdrss.com/ai-agents/agent-design-and-orchestration/901132/901132.md)

This file covers decision heuristics for building agents on the Claude API: which primitives to reach for, how to design your tool surface, and how to manage context and cost over long runs. For per-tool mechanics and code examples, see tool-use-concepts.md and the language-spe. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Managed Agents — Python](https://mdrss.com/ai-agents/agent-design-and-orchestration/901131/901131.md)

List files the agent wrote to /mnt/session/outputs/ during a session, then. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Tool Use — Python](https://mdrss.com/ai-agents/agent-design-and-orchestration/901130/901130.md)

For conceptual overview (tool definitions, tool choice, tips), see shared/tool-use-concepts.md. Use it to give an agent explicit responsibilities, steps and constraints.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:16.866Z · Version: 1

### [Claude API — Python](https://mdrss.com/ai-agents/agent-design-and-orchestration/901129/901129.md)

Use with options() to override client settings for a single call without mutating the client:. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:05.624Z · Version: 1

### [Building LLM-Powered Applications with Claude](https://mdrss.com/ai-agents/agent-design-and-orchestration/901128/901128.md)

This skill helps you build LLM-powered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation. Use it to make implementation decisions and avoid common dead ends.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:05.624Z · Version: 1

### [CoALA: Awesome Language Agents](https://mdrss.com/ai-agents/agent-design-and-orchestration/901127/901127.md)

A compilation of language agents using the Cognitive Architectures for Language Agents (🐨CoALA) framework. - CoALA Paper (16 pages of main content): https://arxiv.org/abs/2309.02427 - CoALA Tweet (6 threads): https://twitter.com/ShunyuYao12/status/1699396834983362690 - CoALA. Use it to navigate the topic and choose relevant methods, papers or tools.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:05.624Z · Version: 1

### [Claude Code: Everything You Need to Know](https://mdrss.com/ai-agents/agent-design-and-orchestration/901125/901125.md)

A practical guide to Claude Code — from your first prompt to multi-agent automation, hooks, MCP, and team workflows. Built around clear mental models and real examples, not marketing. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:05.624Z · Version: 1

### [prompt-injection-defenses](https://mdrss.com/ai-agents/prompting-and-agent-evaluation/901120/901120.md)

This repository centralizes and summarizes practical and proposed defenses against prompt injection. Use it to navigate the topic and choose relevant methods, papers or tools.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:05.624Z · Version: 1

### [Learn Claude Code -- Harness Engineering for Real Agents](https://mdrss.com/ai-agents/agent-design-and-orchestration/901111/901111.md)

At the core of every agent is a neural network -- a Transformer, an RNN, a trained function -- shaped by billions of gradient updates on sequences of perception, reasoning, and action. Agency was never bestowed by the surrounding code. It was learned during training. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:05.624Z · Version: 1

### [Table of Contents](https://mdrss.com/ai-agents/prompting-and-agent-evaluation/901102/901102.md)

Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on Large Language Models and exploring the boundaries and limits of Generative AI. Use it to build a structured path from fundamentals to hands-on practice.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:04.205Z · Version: 1

### [MCP Inspector](https://mdrss.com/ai-agents/mcp-tooling-and-context/901098/901098.md)

A developer tool for inspecting Model Context Protocol (MCP) servers. It ships as a single package, @modelcontextprotocol/inspector, that provides three ways to inspect a server:. Use it to ground design choices in named patterns, trade-offs and examples.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:04.205Z · Version: 1

### [Agent Governance Toolkit](https://mdrss.com/ai-agents/prompting-and-agent-evaluation/901091/901091.md)

Policy enforcement, identity, sandboxing, and SRE for autonomous AI agents. One pip install, any framework. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:04.205Z · Version: 1

### [Awesome OpenClaw Agents](https://mdrss.com/ai-agents/agent-design-and-orchestration/901087/901087.md)

Pick a template, see what it does, get a Dockerfile + docker-compose + bot + README you can run anywhere. Use it as a repeatable review, validation or hardening pass.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:04.205Z · Version: 1

### [PIPE - Prompt Injection Primer for Engineers](https://mdrss.com/ai-agents/prompting-and-agent-evaluation/901077/901077.md)

Bringing clarity to questions about Prompt Injection Security. Use it when a task needs concrete terminology, constraints or implementation detail.

Feed: [ai-agents](https://mdrss.com/s/ai-agents) · Snapshot: 2026-08-04T13:48:02.244Z · Version: 1