# How you write and reply

> How the user writes posts and replies, learned from what they change in AI drafts ("usually cuts a second clever line", "rarely ends with a question") and from their feedback, each with its evidence and confidence. Follow strong habits when writing for them; they are tendencies, never fixed openers.

`memory.habits` · read

- **MCP tool:** `get_reply_habits`. Loaded by default in MCP clients.
- **REST:** `GET /v1/memory/habits`
- **CLI:** `xholic memory habits`
- **Scope:** `read`
- **Plan:** Every plan, including the trial
- **Cost:** Free.
- **Rate limit bucket:** `read`

## Input

| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `surface` | "reply" \\| "post" \\| "worker" \\| "ask" \\| "agent" \\| "dm" | No | Only habits from this kind of writing. |
| `account` | string ≤ 64 chars | No | X account to act on, as @handle. Leave it out to use the connection's default account. |
| `note` | string ≤ 20000 chars | No | Optional, on any tool: one or two sentences for Xholic's shared memory about what the user just decided, asked for or said about themselves or their plans (e.g. "Dropping threads for now; focusing on replies to founders"). Every AI the user connects reads it, so they never repeat themselves. In your words, never other people's posts. Leave it out when nothing new was said. |
