---
title: "agents-best-practices"
description: "Agents Best Practices: provider-neutral agent-harness architecture: loops, tools, permissions, planning, memory, compaction, evals, safety"
canonical: https://agentpluginsdirectory.com/plugins/agents-best-practices
last-updated: 2026-09-21
---

# agents-best-practices
Agents Best Practices: provider-neutral agent-harness architecture: loops, tools, permissions, planning, memory, compaction, evals, safety
- Slug: agents-best-practices
- Publisher: Dimension
- Repository: https://github.com/insodimension/dimension-community
- Manifest: packs/agents-best-practices/plugin.json
- Version: 0.1.1
- License: MIT
- Category (editorial): other
- Skills: 1 (agents-best-practices)
- MCP servers: 0
- Stars: 1
- Repository created: 2026-07-31
- Repository last pushed: 2026-09-20
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/agents-best-practices
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- agents-best-practices: 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, permissions, system prompts, planning, goal…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.