codex

# Codex Bridge Invoke the OpenAI Codex CLI from inside a Claude session. Three subcommands map to three distinct use cases. All subcommands are called via: ```bash bun "$HOME/.claude/src/scripts/codex-run.ts" <subcommand> [args] ``` --- ## Subcommands ### exec -- delegate mechanical or bulk work ```bash bun "$HOME/.claude/src/scripts/codex-run.ts" exec "the full task description" ``` Runs Codex in a `workspace-write` sandbox. Use this when a task is: - Mechanical (repetitive edits, file scaffolding, boilerplate generation) - Bulk (touching many files at once where Claude's serial context would be slow) - Parallelizable with Claude's own work (start Codex on one half while Claude handles the other) **Quota routing**: Codex is metered by messages per ~5-hour window, not by tokens. Hand it one big complete task, not a sequence of small steps. A single `exec` call for a whole feature costs the same quota as one `exec` call for a single file. After `exec` returns, ALWAYS review Codex's diff before trusting it: ```bash git diff ``` Then run the proof gate: ```bash bun run proof ``` ### review -- independent cross-model diff review ```bash bun "$HOME/.claude/src/scripts/codex-run.ts" review ``` Runs in a `read-only` sandbox. Codex reads the repo itself (`git diff`, `git status`) and reports findings by severity (HIGH / MEDIUM / LOW), covering correctness bugs, security issues, and obvious quality problems. Use this after you have finished a diff and want a second o...