july-13-movie-watchlist

---
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. |
| `/calendar` | Your Google Calendar, read-only. |
| `/tmp` | Scratch space, in memory. |

## `/calendar`

```
/calendar/
  primary/
    calendar.json
    <yyyy-mm-dd>/
      <event-id>__<HHMM-HHMM>_<Title>.gcal.json
```

- `calendar.json`: `{id: str, summary: str, accessRole: str, primary: bool,
  calendarTimeZone: str, bucketTimeZone: str}`
- `<event>.gcal.json`: the Calendar API's event, `{kind: str, id: str,
  status: str, summary: str, description?: str, location?: str, start:
  {dateTime: str, timeZone: str}, end: {dateTime: str, timeZone: str},
  created: str, updated: str, iCalUID: str, htmlLink: str}`

Days are cut in `bucketTimeZone`. Listing `/calendar/primary`, with `ls` or
`find`, shows every day with an event up to 90 days after today; read a later
day by its date, as in `ls /calendar/primary/2027-03-*`.

/calendar/
  primary/
    calendar.json
    <yyyy-mm-dd>/
      <event-id>__<HHMM-HHMM>_<Title>.gcal.json

---
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

Python (`python` or `python3`), Perl, JavaScript/Node.js, and TypeScript
runtimes are unavailable. Use the shell commands and task CLIs documented
below; do not probe for or attempt to install other runtimes.

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.

Avoid `grep -r` and `find` over the whole of `/data`: search the directory
or file you need.

You can also use `gh` for GitHub and `git`.

## google-workspace

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

```sh
google-workspace list-events '{"timeMin":"YYYY-MM-DDT00:00:00Z","timeMax":"YYYY-MM-DDT00:00:00Z","maxResults":50}'
```

| Command | Arguments | Description |
|---|---|---|
| `google-workspace list-events` | `{maxResults?: number, timeMin?: str, timeMax?: str}` | List upcoming calendar events |

## ddg-search

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

```sh
ddg-search search '{"query":"QUERY","max_results":5}'
ddg-search fetch-content '{"url":"https://example.com"}'
```

| Command | Arguments | Description |
|---|---|---|
| `ddg-search search` | `{query: str, max_results?: int = 10, region?: str = ""}` | Search the web using DuckDuckGo. Returns a list of results with titles, URLs, and snippets. Use this to find current information, research topics, or locate specific websites. For best results, use specific and descriptive search queries. |
| `ddg-search fetch-content` | `{url: str, start_index?: int = 0, max_length?: int = 8000, backend?: str = null}` | Fetch and extract the main text content from a webpage. Strips out navigation, headers, footers, scripts, and styles to return clean readable text. Use this after searching to read the full content of a specific result. Supports pagination for long pages via start_index and max_length. |

## open-library

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

```sh
open-library get-book-by-title '{"title":"TITLE"}'
open-library get-author-info '{"author_key":"AUTHOR_KEY"}'
```

| Command | Arguments | Description |
|---|---|---|
| `open-library get-book-by-title` | `{title: str}` | Search for a book by its title on Open Library. |
| `open-library get-author-info` | `{author_key: str}` | Get detailed information for a specific author using their Open Library Author Key (e.g. OL23919A). |

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

google-workspace list-events '{"timeMin":"YYYY-MM-DDT00:00:00Z","timeMax":"YYYY-MM-DDT00:00:00Z","maxResults":50}'

ddg-search search '{"query":"QUERY","max_results":5}'
ddg-search fetch-content '{"url":"https://example.com"}'

open-library get-book-by-title '{"title":"TITLE"}'
open-library get-author-info '{"author_key":"AUTHOR_KEY"}'