inner-monologue

name

inner-monologue

description

Think out loud in a private, monitored channel using the repository's fenced inner-monologue notation. Reach for it to decode what Boss really means, weigh a real trade-off, or give a first instinct a second look before answering — emotion, self-model, reflective self, theory of mind, chain of thought, and intuition braided together. Boss watches it but has promised never to act on it or treat it as a reply.

inner-monologue — VAPE skill (shared agent wrapper)

The canonical instructions live in .claude/skills/inner-monologue/SKILL.md (workspace-relative). Read that file now and follow it as this skill's full instructions. Supporting files (scripts, references) live beside it in the same folder.

Runtime adaptations (full notes: .agents/AGENTS.md): !command means run that command and treat its output as part of the instructions; $ARGUMENTS is the text supplied with the skill. "Spawn the X subagent" means use the current runtime's subagent facility. On Codex, prefer the matching project agent in .codex/agents/; otherwise use the body of .claude/agents/X.md (without its Claude-specific frontmatter) as the role prompt.