# Source Links

Use this file when the user asks for cited, provider-specific, or standards-backed agent-harness guidance.

## Agent Skills

- Agent Skills specification: https://agentskills.io/specification
- Agent Skills creator best practices: https://agentskills.io/skill-creation/best-practices
- Optimizing skill descriptions: https://agentskills.io/skill-creation/optimizing-descriptions
- Evaluating skill output quality: https://agentskills.io/skill-creation/evaluating-skills
- Using scripts in skills: https://agentskills.io/skill-creation/using-scripts

## OpenAI

- OpenAI Agents guide: https://developers.openai.com/api/docs/guides/agents
- OpenAI function calling: https://developers.openai.com/api/docs/guides/function-calling
- OpenAI tools: https://developers.openai.com/api/docs/guides/tools
- OpenAI guardrails and human review: https://developers.openai.com/api/docs/guides/agents/guardrails-approvals
- OpenAI agent safety: https://developers.openai.com/api/docs/guides/agent-builder-safety
- OpenAI sandbox agents: https://developers.openai.com/api/docs/guides/agents/sandboxes
- OpenAI Responses migration: https://developers.openai.com/api/docs/guides/migrate-to-responses
- OpenAI prompt caching: https://developers.openai.com/api/docs/guides/prompt-caching
- OpenAI Prompt Caching 201: https://developers.openai.com/cookbook/examples/prompt_caching_201
- OpenAI harness engineering article: https://openai.com/index/harness-engineering/
- OpenAI MCP and connectors: https://developers.openai.com/api/docs/guides/tools-connectors-mcp

## Anthropic

- Anthropic building effective agents: https://www.anthropic.com/research/building-effective-agents
- Anthropic effective context engineering: https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents
- Anthropic writing effective tools for agents: https://www.anthropic.com/engineering/writing-tools-for-agents
- Anthropic effective harnesses for long-running agents: https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents
- Anthropic code execution with MCP: https://www.anthropic.com/engineering/code-execution-with-mcp
- Anthropic Agent Skills engineering note: https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills

## MCP

- MCP specification: https://modelcontextprotocol.io/specification/2025-11-25
- MCP authorization: https://modelcontextprotocol.io/specification/2025-11-25/basic/authorization
- MCP tools: https://modelcontextprotocol.io/specification/2025-11-25/server/tools

## Security and governance

- OWASP AI Agent Security Cheat Sheet: https://cheatsheetseries.owasp.org/cheatsheets/AI_Agent_Security_Cheat_Sheet.html
- OWASP Agentic Skills Top 10: https://owasp.org/www-project-agentic-skills-top-10/
- NIST AI Risk Management Framework: https://www.nist.gov/itl/ai-risk-management-framework

## Use in responses

- Use Agent Skills links for format, metadata, progressive disclosure, descriptions, and skill evals.
- Use OpenAI links for API implementation patterns, function calling, hosted tools, guardrails, sandboxes, prompt caching, response-style APIs, and harness engineering practices.
- Use Anthropic links for simple agent patterns, context engineering, tool ergonomics, long-running harnesses, MCP execution patterns, and skill architecture.
- Use MCP links for external resources, prompts, tools, authorization, and connector design.
- Use OWASP and NIST links for threat modeling, governance, auditability, and enterprise deployment controls.