skill-authoring

1> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.
2> Cross-reference commands use installed skill names in Codex rather than `/octo:*` slash commands.
3> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.
4> For host tool equivalents, see `skills/blocks/codex-host-adapter.md`.
5 
6 
7# Skill Authoring
8 
9Load `skills/blocks/engineering-method-selection.md` from the installed plugin
10and apply only the methods relevant to this task. Preserve this entry point's
11execution contract and output format. Read referenced skills as instructions;
12do not invoke the current command recursively or add provider calls from a seat.
13 
14## Domain language
15 
16Load `skills/blocks/domain-modeling.md` when a skill discusses providers, models,
17access, billing, reviewers, or votes. Reuse the shared definitions instead of
18inventing local synonyms. State the source and time of observations. Never infer
19authentication, entitlement, billing mode, quota, or model-family independence
20from a binary or transport name alone.
21 
22A skill exists to get determinism out of a stochastic system. **Predictability**
23is the goal, and it means the agent takes the same *process* every run — not that
24it produces the same output. Every rule below serves that.
25 
26`docs/PLUGIN-ASSEMBLY-STANDARD.md` already fixes the *structure* a skill body
27…