Experimental. Hooks are under active development. Windows support temporarily disabled.
Hooks are an extensibility framework for Codex. They allow you to inject your own scripts into the agentic loop, enabling features such as:
- Send the conversation to a custom logging/analytics engine
- Scan your team’s prompts to block accidentally pasting API keys
- Summarize conversations to create persistent memories automatically
- Run a custom validator when a conversation turn stops, enforcing standards
- Customize prompting when in a certain directory
Hooks are behind a feature flag in config.toml:
[features]
codex_hooks = true
Runtime behavior to keep in mind:
- Matching hooks from multiple files all run.
- Multiple matching command hooks for the same event are launched concurrently, so one hook cannot prevent another matching hook from starting.
PreToolUse,PostToolUse,UserPromptSubmit, andStoprun at turn scope.- Hooks are currently disabled on Windows.
Where Codex looks for hooks
Codex discovers hooks.json next to active config layers.
In practice, the two most useful locations are:
~/.codex/hooks.json<repo>/.codex/hooks.json
If more than one hooks.json file exists, Codex loads all matching hooks.
Higher-precedence config layers do not replace lower-precedence hooks.
Config shape
Hooks are organized in three levels:
- A hook event such as
PreToolUse,PostToolUse, orStop - A matcher group that decides when that event matches
- One or more hook handlers that run when the matcher group matches
{
"hooks": {
"SessionStart": [
{
"matcher": "startup|resume",
"hooks": [
{
"type": "command",
"command": "python3 ~/.codex/hooks/session_start.py",
"statusMessage": "Loading session notes"
}
]
}
],
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "/usr/bin/python3 \"$(git rev-parse --show-toplevel)/.codex/hooks/pre_tool_use_policy.py\"",
"statusMessage": "Checking Bash command"
}
]
}
],
"PostToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "/usr/bin/python3 \"$(git rev-parse --show-toplevel)/.codex/hooks/post_tool_use_review.py\"",
"statusMessage": "Reviewing Bash output"
}
]
}
],
"UserPromptSubmit": [
{
"hooks": [
{
"type": "command",
"command": "/usr/bin/python3 \"$(git rev-parse --show-toplevel)/.codex/hooks/user_prompt_submit_data_flywheel.py\""
}
]
}
],
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "/usr/bin/python3 \"$(git rev-parse --show-toplevel)/.codex/hooks/stop_continue.py\"",
"timeout": 30
}
]
}
]
}
}
Notes:
timeoutis in seconds.timeoutSecis also accepted as an alias.- If
timeoutis omitted, Codex uses600seconds. statusMessageis optional.- Commands run with the session
cwdas their working directory. - For repo-local hooks, prefer resolving from the git root instead of using a
relative path such as
.codex/hooks/.... Codex may be started from a subdirectory, and a git-root-based path keeps the hook location stable.
Matcher patterns
The matcher field is a regex string that filters when hooks fire. Use "*",
"", or omit matcher entirely to match every occurrence of a supported
event.
Only some current Codex events honor matcher:
| Event | What matcher filters | Notes |
|---|---|---|
PostToolUse | tool name | Current Codex runtime only emits Bash. |
PreToolUse | tool name | Current Codex runtime only emits Bash. |
SessionStart | start source | Current runtime values are startup and resume. |
UserPromptSubmit | not supported | Any configured matcher is ignored for this event. |
Stop | not supported | Any configured matcher is ignored for this event. |
Examples:
Bashstartup|resumeEdit|Write
That last example is still a valid regex, but current Codex PreToolUse and
PostToolUse events only emit Bash, so it will not match anything today.
Common input fields
Every command hook receives one JSON object on stdin.
These are the shared fields you will usually use:
| Field | Type | Meaning |
|---|---|---|
session_id | string | Current session or thread id. |
transcript_path | string | null | Path to the session transcript file, if any |
cwd | string | Working directory for the session |
hook_event_name | string | Current hook event name |
model | string | Active model slug |
Turn-scoped hooks list turn_id in their event-specific tables.
If you need the full wire format, see Schemas.
Common output fields
SessionStart, UserPromptSubmit, and Stop support these shared JSON
fields:
{
"continue": true,
"stopReason": "optional",
"systemMessage": "optional",
"suppressOutput": false
}
| Field | Effect |
|---|---|
continue | If false, marks that hook run as stopped |
stopReason | Recorded as the reason for stopping |
systemMessage | Surfaced as a warning in the UI or event stream |
suppressOutput | Parsed today but not yet implemented |
Exit 0 with no output is treated as success and Codex continues.
PreToolUse supports systemMessage, but continue, stopReason, and
suppressOutput are not currently supported for that event.
PostToolUse supports systemMessage, continue: false, and stopReason.
suppressOutput is parsed but not currently supported for that event.
Hooks
SessionStart
matcher is applied to source for this event.
Fields in addition to Common input fields:
| Field | Type | Meaning |
|---|---|---|
source | string | How the session started: startup or resume |
Plain text on stdout is added as extra developer context.
JSON on stdout supports Common output fields and this
hook-specific shape:
{
"hookSpecificOutput": {
"hookEventName": "SessionStart",
"additionalContext": "Load the workspace conventions before editing."
}
}
That additionalContext text is added as extra developer context.
PreToolUse
Currently PreToolUse only supports Bash tool interception. The model can
still work around this by writing its own script to disk and then running that
script with Bash, so treat this as a useful guardrail rather than a complete
enforcement boundary.
matcher is applied to tool_name, which currently always equals Bash.
Fields in addition to Common input fields:
| Field | Type | Meaning |
|---|---|---|
turn_id | string | Codex-specific extension. Active Codex turn id |
tool_name | string | Currently always Bash |
tool_use_id | string | Tool-call id for this invocation |
tool_input.command | string | Shell command Codex is about to run |
Plain text on stdout is ignored.
JSON on stdout can use systemMessage and can block a Bash command with this
hook-specific shape:
{
"hookSpecificOutput": {
"hookEventName": "PreToolUse",
"permissionDecision": "deny",
"permissionDecisionReason": "Destructive command blocked by hook."
}
}
Codex also accepts this older block shape:
{
"decision": "block",
"reason": "Destructive command blocked by hook."
}
You can also use exit code 2 and write the blocking reason to stderr.
permissionDecision: "allow" and "ask", legacy decision: "approve",
updatedInput, additionalContext, continue: false, stopReason, and
suppressOutput are parsed but not supported yet, so they fail open.
PostToolUse
Currently PostToolUse only supports Bash tool results. It is not limited to
commands that exit successfully: non-interactive exec_command calls can still
trigger PostToolUse when Codex emits a Bash post-tool payload. It cannot undo
side effects from the command that already ran.
matcher is applied to tool_name, which currently always equals Bash.
Fields in addition to Common input fields:
| Field | Type | Meaning |
|---|---|---|
turn_id | string | Codex-specific extension. Active Codex turn id |
tool_name | string | Currently always Bash |
tool_use_id | string | Tool-call id for this invocation |
tool_input.command | string | Shell command Codex just ran |
tool_response | JSON value | Bash tool output payload. Today this is usually a JSON string |
Plain text on stdout is ignored.
JSON on stdout can use systemMessage and this hook-specific shape:
{
"decision": "block",
"reason": "The Bash output needs review before continuing.",
"hookSpecificOutput": {
"hookEventName": "PostToolUse",
"additionalContext": "The command updated generated files."
}
}
That additionalContext text is added as extra developer context.
For this event, decision: "block" does not undo the completed Bash command.
Instead, Codex records the feedback, replaces the tool result with that
feedback, and continues the model from the hook-provided message.
You can also use exit code 2 and write the feedback reason to stderr.
To stop normal processing of the original tool result after the command has
already run, return continue: false. Codex will replace the tool result with
your feedback or stop text and continue from there.
updatedMCPToolOutput and suppressOutput are parsed but not supported yet,
so they fail open.
UserPromptSubmit
matcher is not currently used for this event.
Fields in addition to Common input fields:
| Field | Type | Meaning |
|---|---|---|
turn_id | string | Codex-specific extension. Active Codex turn id |
prompt | string | User prompt that is about to be sent |
Plain text on stdout is added as extra developer context.
JSON on stdout supports Common output fields and
this hook-specific shape:
{
"hookSpecificOutput": {
"hookEventName": "UserPromptSubmit",
"additionalContext": "Ask for a clearer reproduction before editing files."
}
}
That additionalContext text is added as extra developer context.
To block the prompt, return:
{
"decision": "block",
"reason": "Ask for confirmation before doing that."
}
You can also use exit code 2 and write the blocking reason to stderr.
Stop
matcher is not currently used for this event.
Fields in addition to Common input fields:
| Field | Type | Meaning |
|---|---|---|
turn_id | string | Codex-specific extension. Active Codex turn id |
stop_hook_active | boolean | Whether this turn was already continued by Stop |
last_assistant_message | string | null | Latest assistant message text, if available |
Stop expects JSON on stdout when it exits 0. Plain text output is invalid
for this event.
JSON on stdout supports Common output fields. To keep
Codex going, return:
{
"decision": "block",
"reason": "Run one more pass over the failing tests."
}
You can also use exit code 2 and write the continuation reason to stderr.
For this event, decision: "block" does not reject the turn. Instead, it tells
Codex to continue and automatically creates a new continuation prompt that acts
as a new user prompt, using your reason as that prompt text.
If any matching Stop hook returns continue: false, that takes precedence
over continuation decisions from other matching Stop hooks.
Schemas
If you need the exact current wire format, see the generated schemas in the Codex GitHub repository.