Skip to content
Tools/Harness / Safety
Harness / SafetyCommunityOpen source

agents-best-practices

Provider-neutral Agent Skill for designing, auditing, and refactoring agent harnesses — installable for both Codex and Claude Code.

Visit source

Key capabilities

Core principle: the model proposes actions; the harness validates, authorizes, executes, records, and returns observations.
Installs as a skill under ~/.codex/skills or ~/.claude/skills

Best for

Harness design principles
Validation and authorization gates
Project instructions

Not for

Stack-specific assumptions without adaptation

Risk notes

Adapt the rules to your own stack and permissions.
This is a community project. Verify maturity, licensing, permissions, and safety behavior before relying on it in production.