codex-frameworklisted
Install: claude install-skill nxtg-ai/forge-plugin
# Codex CLI — Reference Knowledge
> **REFERENCE ONLY.** Do NOT create `AGENTS.md`, `AGENTS.override.md`, `SKILLS.md`, or `.agents/`
> on your own initiative. NXTG-Forge delivers agents and skills through the **Claude Code plugin**
> system, not Codex-style files. Only scaffold Codex files when the user **explicitly** asks to add
> Codex support (see the worked example below).
## How Codex CLI discovers instructions (AGENTS.md)
Codex builds one instruction chain per run by **concatenating** files from two layers, joined by
blank lines — it does NOT pick a single "winning" file:
1. **Home layer** (`~/.codex`, or `$CODEX_HOME`): reads `AGENTS.override.md` if present, else
`AGENTS.md`. First non-empty file at this level only.
2. **Project layer**: from the project root (usually the git root) walking **down** to the current
working directory, in each directory it takes at most one of: `AGENTS.override.md`, then
`AGENTS.md`, then any name in `project_doc_fallback_filenames` (config-driven). All matched files
are concatenated root-first.
A nested `AGENTS.md` in a subdirectory **adds to** (does not replace) the root one — closer files
come later in the concatenation, so they refine rather than override.
Rough Claude Code analogues (not 1:1 — see Gotchas):
- `CLAUDE.md` ↔ `AGENTS.md` (repo-wide instruction file)
- `.claude/agents/*.md` ↔ persona/role blocks written inline in `AGENTS.md`
- `.claude/skills/*/SKILL.md` ↔ `.agents/skills/*/SKILL.md`
## How Codex discove