romarayt/raytsystem-public-os

Local-first agent workspace for knowledge, tasks, documents and verifiable workflows · Local agent system for knowledge, tasks and verifiable processes · t.me/romarayt

12 files for Claude Code, Codex and OpenCode: graph, ingest, lint, query and 8 more — 1,295 tokens loaded in every session.

Open on GitHub romarayt.github.io

Instructions

raytsystem-public-os AGENTS.md AGENTS.md A 684 tok
raytsystem-public-os CLAUDE.md CLAUDE.md A 611 tok

Skills

graph .agents/skills/graph/SKILL.md A 46 tok
ingest .agents/skills/ingest/SKILL.md A 69 tok
lint .agents/skills/lint/SKILL.md A 55 tok
query .agents/skills/query/SKILL.md A 57 tok
research .agents/skills/research/SKILL.md A 56 tok
run-review .agents/skills/run-review/SKILL.md A 59 tok
save .agents/skills/save/SKILL.md A 50 tok
security-review .agents/skills/security-review/SKILL.md A 66 tok
start .agents/skills/start/SKILL.md A 53 tok
watch .agents/skills/watch/SKILL.md A 111 tok

These files are romarayt/raytsystem-public-os'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.