The collaboration layer for AI teams: domain experts review and annotate agent behavior, engineers improve the agent from what they find.
Latest release v0.20.1 — Platform v0.20.1 · 3 Nov 2026
18 files for Claude Code, Codex and OpenCode: backend-debug, backend-testing, docs-design-tokens, docs-social-images and 14 more — 1,614 tokens loaded in every session.
AGENTS.md A 1,609 tok CLAUDE.md A 5 tok .claude/settings.json A — .claude/settings.json A — .claude/settings.json A — .agents/skills/backend-debug/SKILL.md A 30 tok .agents/skills/backend-testing/SKILL.md A 34 tok .agents/skills/docs-design-tokens/SKILL.md A 46 tok .agents/skills/docs-social-images/SKILL.md A 45 tok .agents/skills/ee-feature/SKILL.md A 31 tok .agents/skills/github-issue/SKILL.md A 34 tok .agents/skills/playground-script/SKILL.md A 37 tok .agents/skills/pull-request/SKILL.md A 38 tok .agents/skills/python-linting/SKILL.md A 32 tok .agents/skills/update-branch/SKILL.md A 38 tok .agents/skills/worktree/SKILL.md A 46 tok .claude/commands/fix-secdeps.md A 12 tok .claude/commands/peqy.md A 16 tok These files are rhesis-ai/rhesis'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.