agents-best-practices

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

What is agents-best-practices?

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

Overview of agents-best-practices

What it is

A provider-neutral Agent Skill for designing, generating MVP blueprints for, auditing, refactoring, and explaining agentic harnesses. It applies beyond coding agents to research, support, operations, sales, finance, data analysis, procurement, legal workflows, healthcare workflows, education, and workflow automation agents.

Key features

  • Provider-neutral design compatible with Codex, Claude Code, and other agentic harnesses.
  • Generates MVP agent blueprints with structured core loops, typed tools, and launch gates.
  • Audits existing agent harnesses for runtime-level failure points such as missing budgets, unbounded tool results, and poor compaction.
  • Guides design of tools, permissions, and connectors split by risk class.
  • Supports late-bound tool environments with discovery, probes, and runtime binding.
  • Provides references for agentic loop, context/memory/compaction, security/observability, evals, and more.

Use cases

Once installed, the skill activates when a conversation touches agent architecture, harness design, tool permissions, environment-adaptive tools, speculative tool execution, planning mode, workflow orchestration, adaptive agent teams, context and memory, skills, connectors, public-board communication, troubleshooting, observability, evals, prompt caching, or production readiness. Ten common use cases are documented, including generating an MVP agent blueprint, auditing an existing agent harness, designing tools/permissions/connectors, adapting to a late-bound tool environment, and designing a self-refining recursive harness.

Getting started

Install via one of the following methods:A. With skills (any compatible agent):bashnpx skills add DenisSergeevitch/agents-best-practices -gB. Or paste a prompt to your AI agent to clone the repository into your user-level skills directory.****C. Manual install paths:bash# Codexmkdir -p "${CODEX_HOME:-$HOME/.codex}/skills"git clone https://github.com/DenisSergeevitch/agents-best-practices.git "${CODEX_HOME:-$HOME/.codex}/skills/agents-best-practices"# Claude Code, user-levelmkdir -p "$HOME/.claude/skills"git clone https://github.com/DenisSergeevitch/agents-best-practices.git "$HOME/.claude/skills/agents-best-practices"# Claude Code, project-levelmkdir -p .claude/skillsgit clone https://github.com/DenisSergeevitch/agents-best-practices.git .claude/skills/agents-best-practices

License and pricing

License: MIT. Pricing type: open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/denissergeevitchagents-best-practices.svg)](https://yunodb.com/tools/denissergeevitchagents-best-practices?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/denissergeevitchagents-best-practices?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/denissergeevitchagents-best-practices.svg" alt="Featured on YunoDB" height="20"></a>