Codex runtime mapping

Use skill-creator for authoring, cursor-unslop for prose, and cursor-poteto-mode only as a shape example. Search .agents/skills/ in the project and the personal Codex skills root only when it is relevant and readable. Mine bounded history from the current workspace/task, never unrelated task roots. Native user-input surfaces may allow fewer choices and no multiselect; retain the broad-to-specific preference inquiry in concise rounds with free text. Project-local writes follow the current task scope; personal installation is a separate explicit choice.

Automate me

A guided flow for turning the user's working conventions into a skill agents will follow. The output is one -mode skill tailored to them (e.g. jay-mode, priya-mode).

This skill orchestrates three others: an inline mining pass (see step 1), the native skill-creator (authoring), and the cursor-unslop skill (prose discipline). It sequences them. It doesn't replace them.

Flow

0. Check for an existing skill

Look recursively for .agents/skills/**/*-mode/SKILL.md and the personal Codex skills root (~/.codex/skills/*-mode/SKILL.md, when relevant and readable) matching the user's handle. Mode skills can live in a personal category directory (.agents/skills/<handle>/), not only at the top level. If one exists, confirm intent through the native optional user-input surface (unless they already said "update my skill" or similar):

• Update the existing skill (default for repeat runs)
• Start fresh (rare, ask why before doing it)