diff --git a/sdk/guides/hooks.mdx b/sdk/guides/hooks.mdx
index 72ec3f26..2ceefb87 100644
--- a/sdk/guides/hooks.mdx
+++ b/sdk/guides/hooks.mdx
@@ -25,6 +25,27 @@ Hooks let you observe and customize key lifecycle moments in the SDK without for
 | SessionStart | When conversation starts | No |
 | SessionEnd | When conversation ends | No |
 
+## Exit Codes
+
+Hook scripts signal their result through their exit code. The SDK matches the
+[Claude Code hook contract](https://docs.claude.com/en/docs/claude-code/hooks):
+
+- **`0` — success.** The operation proceeds. `stdout` is parsed as JSON for
+  structured output (`decision`, `reason`, `additionalContext`, `continue`).
+- **`2` — block.** The operation is denied. For `PreToolUse` and
+  `UserPromptSubmit` this rejects the action; for `Stop` it prevents the
+  agent from finishing and the conversation continues. `stderr` / `reason`
+  is surfaced as feedback.
+- **Any other non-zero exit code — non-blocking error.** `success` is set to
+  `False` and the error is logged via `HookExecutionEvent`, but the
+  operation still proceeds.
+
+<Warning>
+Only exit code `2` blocks. Exit code `1` (the conventional Unix failure
+code) is treated as a non-blocking error. A hook intended to enforce a
+policy must exit with `2`.
+</Warning>
+
 ## Key Concepts
 
 - Registration points: subscribe to events or attach pre/post hooks around LLM calls and tool execution