§1 — Scope and sources

This audit compares the current Codex instruction and skill-loading contract with the workstation conventions built for Claude Code. Sources were the official Codex manual, the user-global agent file, repository and nested agent files in Ambix and Nova, the installed user skill directories, and live Codex skill discovery in this session.

§2 — Findings

SurfaceObserved contractGap
User instructionsCodex looks for ~/.codex/AGENTS.md.The canonical workstation file is ~/.agents/AGENTS.md; the Codex entrypoint is absent.
Project instructionsCodex builds one root-to-launch-directory chain.Nested files below the launch directory are not dynamically added when later editing those paths.
Context budgetProject instruction bytes are capped by configuration.Ambix root plus nested guidance exceeds the default 32 KiB budget.
SkillsMetadata is discovered from user and repository .agents/skills; bodies load when triggered.Useful Claude-only skills are not visible, and two HPC copies are stale against current H200 policy.
NovaMain and develop checkouts carry different root instructions.Stale branch guidance includes git actions prohibited by the current global policy.

§3 — Required evidence

The implementation must include black-box Codex launches from repository root and nested directories, captured instruction-chain manifests, byte-limit tests, skill metadata/body activation tests, and negative fixtures proving stale or out-of-scope files are not silently treated as loaded. Evidence must record Codex version and configuration.