DenisSergeevitch/agents-best-practices

Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.

About the project

agents-best-practices is a provider-neutral guide for designing and evaluating agent harnesses, the runtimes that authorize, execute, observe, and record an AI agent's actions. It serves people building agents for coding, research, operations, and other structured workflows. The catalogue skill is the project's own workflow for generating, auditing, refactoring, and explaining these harnesses.

Open on GitHub

2.3kStars on the repository

1Mods indexed here, across every type

3d agoLast push, which is what freshness is scored on

MITLicence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 1 mods

agents-best-practices

DenisSergeevitch/agents-best-practices

Skill Claude CodeCodex

Use this skill when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, environment-adaptive tools, speculative tool execution…

not rated 2.3k +3 changed 3d ago A 129 tokens original MIT