Tag · 6 notes
Claude Code
Notes on Claude Code, the coding agent in the terminal, and on extending it with output styles, skills, hooks and mods.
2026
A skill description can't make a model want the skillWhen a skill trigger probe fails, check what the model did instead. A model busy doing the task itself may not load any skill.
tilWhere should a decision model decide?A model choice can happen per request, turn, subagent, session, or after failures. Each timing trades cache reuse for precision.
write-upRead a coding agent's model list without logging inCodex and Claude Code both ship their model picker data inside the installed package. You can read it without an account.
tilRabe: see what Claude Code runs in the backgroundRabe is a Claude Code mod that shows agents, Codex jobs, shells, monitors, crons and workflows in one band and one pane.
write-upRoute one Claude Code request to another modelClaude Code hooks can watch a session, but a mod can route one model request elsewhere and change its effort.
tilMy own output styles in Claude CodeClaude Code can answer in a style you write yourself, and you can switch styles to fit the situation.
til