Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.
These files are ReflexioAI/reflexio's own configuration. They tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
AGENTS.md A 128 tok CLAUDE.md A 128 tok .agents/skills/agent-browser/SKILL.md A 108 tok .agents/skills/fastapi/SKILL.md A 57 tok .agents/skills/prd/SKILL.md A 60 tok .agents/skills/ralph/SKILL.md A 64 tok .agents/skills/sync-agent-instructions/SKILL.md A 61 tok .agents/skills/update-public-docs/SKILL.md A 57 tok .claude/commands/check-and-test/SKILL.md A 97 tok .claude/commands/commit/SKILL.md A 122 tok .claude/commands/create-pr/SKILL.md A 74 tok .claude/commands/review/SKILL.md A 52 tok .claude/commands/run-services/SKILL.md C 38 tok .claude/commands/update-pr/SKILL.md A 71 tok