Codex CLI hooks accept plain stdout as context
Adding prompt-preprocessing automation to a CLI agent loop.
Codex CLI ships a full hooks system (UserPromptSubmit, PreToolUse, PostToolUse, PermissionRequest, SessionStart, Stop) gated behind a feature flag — codex_hooks = true under [features] in ~/.codex/config.toml, then registered in ~/.codex/hooks.json. The non-obvious part: for UserPromptSubmit and a couple other events, plain text on stdout is automatically treated as additionalContext appended to the user prompt — no JSON wrapping, exit code 0, just echo the context you want injected. That collapses what would be a 30-line jq-and-printf hook script into 5 lines, and lets you build prompt-preprocessing pipelines (image transcription, repo state injection, etc.) without learning a hook-specific output schema.
For any CLI agent suspected of having hooks, search for <tool> hooks on the official docs site before assuming it does not. The feature-flag-gated pattern hides it from --help output but does not mean the system does not exist.