agents-best-practices
Runtime discipline for building agents, with use cases from blueprints to audits.
Install
npx skills add DenisSergeevitch/agents-best-practices -a claude-code
npx skills add DenisSergeevitch/agents-best-practices -a claude-code -g
Or copy the skill folder into .claude/skills/ (project) or ~/.claude/skills/ (all projects).
npx skills add DenisSergeevitch/agents-best-practices -a codex
npx skills add DenisSergeevitch/agents-best-practices -a codex -g
Or copy the skill folder into .agents/skills/ (project) or ~/.agents/skills/ (all projects).
Run npx skills add DenisSergeevitch/agents-best-practices -g.
When to use
Use it when you're building or reviewing an agent and want a checklist for the parts around the model: tool permissions, validation, logging and error handling.
Agents Best Practices is a provider-neutral skill for designing, auditing, refactoring and explaining agent harnesses. Its core idea is a sentence from the README: the model proposes actions, and the harness validates, authorizes, executes, records and returns observations.
It isn't only for coding agents. The README names research, support, operations, sales, finance, data analysis, procurement, legal, healthcare, education and workflow automation agents as users of the same runtime discipline. Use cases include generating an MVP agent blueprint, auditing an existing harness, and designing tools, permissions and connectors. Install it globally with npx skills add DenisSergeevitch/agents-best-practices -g.
Related skills
-
rea
Lets your agent reverse engineer an app from the outside, down to native binaries, and then build its own version.
-
superpowers
A set of development habits for your agent: test first, debug systematically, and plan before you code.
-
skills
The skills Matt Pocock uses in his own day-to-day engineering work.
-
ECC
A ready-made setup for coding agents that adds skills, persistent memory and security checks.