great-recession-apartments-built

---
name: workspace-filesystem
description: The virtual filesystem layout of this workspace.
---

# Virtual Filesystem

You work in a terminal over a virtual filesystem. Read files with shell
commands.

Command output comes back whole, however long. Some files here are large,
so point `grep -r`, `rg`, `find` and `cat` at the directory or file you
need rather than at a whole mount.

| path | what it is |
|---|---|
| `/data` | Your files. |
| `/notion` | Your Notion workspace, read-only. |
| `/tmp` | Scratch space, in memory. |

## `/notion`

```
/notion/
  pages/
    <page-title>__<page-id>/
      page.json
      <child-page-title>__<child-id>/
        page.json
  databases/
    <database-title>__<database-id>/
      database.json
      <data-source-title>__<data-source-id>/
        data_source.json
        rows.jsonl
```

A title in a path is sanitized: spaces and characters unsafe in a shell
become `_`. `ls` the parent directory for the exact name, or take a row's
`path` from `rows.jsonl`.

- `database.json`: `{database_id: str, title: str, url: str | null,
  created_time: str | null, last_edited_time: str | null, parent: dict,
  archived: bool, is_inline: bool, data_sources: list[{id: str, name: str}]}`
- `data_source.json`: `{data_source_id: str, database_id: str, title: str,
  created_time: str | null, last_edited_time: str | null, database_parent:
  dict, archived: bool, properties: {<column>: {id: str, name: str, type:
  str, <type>: dict}}}`
- `rows.jsonl`: one row per line, `{page_id: str, title: str, path: str,
  url: str, created_time: str, last_edited_time: str, parent_type: str,
  parent_id: str, archived: bool, created_by: str, last_edited_by: str,
  properties: {<column>: {id: str, type: str, <type>: <value>}}}`. Row
  directories are not listed; a row's `page.json` is at its `path` below the
  data source directory. A table's `rows.jsonl` can run to several
  megabytes.
- `page.json`: a row's fields less `path`, plus `markdown: str`, the body,
  and `blocks: list[dict]`

/notion/
  pages/
    <page-title>__<page-id>/
      page.json
      <child-page-title>__<child-id>/
        page.json
  databases/
    <database-title>__<database-id>/
      database.json
      <data-source-title>__<data-source-id>/
        data_source.json
        rows.jsonl

---
name: workspace-commands
description: Use when running commands in this workspace - which commands exist, what they can do, and what the interpreter supports.
---

# Available commands

Standard Unix commands, among them:

    cat  head  tail  ls  find  grep  wc  sort  uniq  cut  tr  sed  awk
    diff  tee  xargs  jq

with pipes, `>` redirection and `$(...)` substitution.

Do not probe the machine with `which`, `type`, `--version`, `env`, `ps`,
`echo $PATH`, `ls /usr/bin` or `cat /usr/bin/<command>`: they tell you
nothing about the task.

A filename with a space in it needs quoting, as it would in any shell.

## notion

Use `notion <command> '<JSON arguments>'`. Run `notion <command> --help` to
get more information.

```sh
notion post-database-query '{"database_id":"ID","filter":{"property":"Name","rich_text":{"contains":"TEXT"}},"page_size":10}'
notion post-search '{"query":"QUERY"}'
notion get-block-children '{"block_id":"ID"}'
notion retrieve-a-block '{"block_id":"ID"}'
```

| Command | Arguments | Description |
|---|---|---|
| `notion post-database-query` | `{database_id: str, filter_properties?: list[str], filter?: dict, sorts?: list[{property: str, direction: "ascending" \| "descending"}], start_cursor?: str, page_size?: int = 100, archived?: bool, in_trash?: bool}` | Query a database |
| `notion post-search` | `{query?: str, sort?: {direction?: str, timestamp?: str}, filter?: {value?: str, property?: str}, start_cursor?: str, page_size?: int = 100}` | Search by title |
| `notion get-block-children` | `{block_id: str, start_cursor?: str, page_size?: int = 100}` | Retrieve block children |
| `notion retrieve-a-block` | `{block_id: str}` | Retrieve a block |

## oxylabs

Use `oxylabs <command> '<JSON arguments>'`. Run `oxylabs <command> --help`
to get more information.

```sh
oxylabs universal-scraper '{"url":"https://example.com","output_format":"md"}'
oxylabs google-search-scraper '{"query":"QUERY"}'
```

| Command | Arguments | Description |
|---|---|---|
| `oxylabs universal-scraper` | `{url: str, render?: "" \| "html" = "", user_agent_type?: "" \| "desktop" \| "desktop_chrome" \| "desktop_firefox" \| "desktop_safari" \| "desktop_edge" \| "desktop_opera" \| "mobile" \| "mobile_ios" \| "mobile_android" \| "tablet" = "", geo_location?: str = "", output_format?: "" \| "links" \| "md" \| "html" = ""}` | Get a content of any webpage. |
| `oxylabs google-search-scraper` | `{query: str, parse?: bool = true, render?: "" \| "html" = "", user_agent_type?: "" \| "desktop" \| "desktop_chrome" \| "desktop_firefox" \| "desktop_safari" \| "desktop_edge" \| "desktop_opera" \| "mobile" \| "mobile_ios" \| "mobile_android" \| "tablet" = "", start_page?: int = 0, pages?: int = 0, limit?: int = 0, domain?: str = "", geo_location?: str = "", locale?: str = "", ad_mode?: bool = false, output_format?: "" \| "links" \| "md" \| "html" = ""}` | Scrape Google Search results. |

## context7

Use `context7 <command> '<JSON arguments>'`. Run `context7 <command> --help`
to get more information.

```sh
context7 resolve-library-id '{"libraryName":"LIBRARY"}'
context7 get-library-docs '{"context7CompatibleLibraryID":"/ORG/PROJECT","topic":"TOPIC"}'
```

| Command | Arguments | Description |
|---|---|---|
| `context7 resolve-library-id` | `{libraryName: str}` | Resolves a package/product name to a Context7-compatible library ID and returns a list of matching libraries. |
| `context7 get-library-docs` | `{context7CompatibleLibraryID: str, topic?: str, tokens?: number}` | Fetches up-to-date documentation for a library. You must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query. |

## e2b-server

Use `e2b-server <command> '<JSON arguments>'`. Run
`e2b-server <command> --help` to get more information.

```sh
e2b-server run-code '{"code":"print(1 + 1)"}'
```

| Command | Arguments | Description |
|---|---|---|
| `e2b-server run-code` | `{code: str}` | Run python code in a secure sandbox by E2B. Using the Jupyter Notebook syntax. |

## fetch

Use `fetch <command> '<JSON arguments>'`. Run `fetch <command> --help` to
get more information.

```sh
fetch fetch '{"url":"https://example.com"}'
```

| Command | Arguments | Description |
|---|---|---|
| `fetch fetch` | `{url: str, max_length?: int = 5000, start_index?: int = 0, raw?: bool = false}` | Fetches a URL from the internet and optionally extracts its contents as markdown. |

## memory

Use `memory <command> '<JSON arguments>'`. Run `memory <command> --help` to
get more information.

```sh
memory read-graph '{}'
```

| Command | Arguments | Description |
|---|---|---|
| `memory read-graph` | `{}` | Read the entire knowledge graph |

## python3

Execute Python code and return stdout and stderr. Code can be pasted into a
`.py` file and run with `python3`. Python cannot launch subprocesses or make
direct network requests. Run the documented service commands directly in
the shell. Use Python for local file processing and generating JSON
arguments.

cat  head  tail  ls  find  grep  wc  sort  uniq  cut  tr  sed  awk
diff  tee  xargs  jq

notion post-database-query '{"database_id":"ID","filter":{"property":"Name","rich_text":{"contains":"TEXT"}},"page_size":10}'
notion post-search '{"query":"QUERY"}'
notion get-block-children '{"block_id":"ID"}'
notion retrieve-a-block '{"block_id":"ID"}'

oxylabs universal-scraper '{"url":"https://example.com","output_format":"md"}'
oxylabs google-search-scraper '{"query":"QUERY"}'

context7 resolve-library-id '{"libraryName":"LIBRARY"}'
context7 get-library-docs '{"context7CompatibleLibraryID":"/ORG/PROJECT","topic":"TOPIC"}'

e2b-server run-code '{"code":"print(1 + 1)"}'

fetch fetch '{"url":"https://example.com"}'

memory read-graph '{}'