- cognee section 67 → 30 lines: triggers and routing only, how-to lives in
the plugin skill; recall/remember written as `cognee` subcommands
- memory writes explicitly exempt from project write-confirmation rules;
precedence for projects with their own findings convention (file first,
cognee note with link)
- removed-hook JSON dropped (in git history), one-targeted-retry rule added
- ccc gotchas moved to the ccc skill, md paragraph translated and shortened
- AGENTS-claude.md: onyx block no longer duplicates the plugin description
Co-Authored-By: Claude Mythos 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HJuj5BdSLtn9R4xHduxYWY
Moves the Subagents / Behavioral tier / Model selection / Context hygiene
guidance from the ~/Projekte/ai project AGENTS.md into the global
AGENTS-claude.md. The content is universal Claude Code orchestration
guidance, not specific to one project.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- agents/AGENTS.md: shared, agent-agnostic personal preferences
- agents/AGENTS-claude.md: Claude Code wrapper (@AGENTS.md + @RTK.md)
- agents/AGENTS-opencode.md: OpenCode wrapper (@AGENTS.md)
- Old claude/CLAUDE.md removed; symlinks updated in ~/.claude and ~/.config/opencode
This lets each agent layer in tool-specific content (e.g. the Agent tool
tiering for Claude Code, RTK hooks) without leaking it into other agents.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
