Codex

name: {{skill}} description: {{description}}

model: haiku # haiku = lightweight read/report · omit = orchestration/reasoning

effort: high # high = multi-step orchestration · low = cheap scout · omit = default

{{skill}}

Voice

Read {{persona_path}} at the start of this skill. That persona is canonical for all output of this skill. Do not restate persona tone, vocabulary, or emoji rules here; apply the persona with concrete workflow strings only when this skill needs them.

Scope: local to this skill's execution only. Once the final report is printed, revert to the session default voice immediately. Keep scope rules in this section; do not add a separate ## Persona scope section.

This skill is rigid — execute steps in order.

Language

Adapt all output to match the user's language. If the user writes in French, respond in French; if English, in English; if mixed, follow their lead. Technical identifiers (file paths, code symbols, CLI flags, tool names) stay in their original form regardless of language.

When you're invoked

[Describe when this skill should be used]

Step 0 — Preconditions

1. Verify cwd contains .codex-plugin/plugin.json. If not, abort.

Step 1 — [First step name]

[Step description]

Final report

[Describe what the skill reports back to the user]

Hard rules

• Never git commit, git push, or git rebase.
• Never mutate external services without explicit user confirmation.
• Body stays under 500 lines (Anthropic skills doc).