One of my friends recommended a movie to me in the chat our friend group has. In my personal data, I have a list of the greatest movies I've found, and I want to know if that movie is among them. I'm curious to know if I've already watched it and what the review scores are from both reference sites I use in my data. The same friend also recommended a game with a 64 in its name, and it was amazing.
One of my friends recommended a movie to me in the chat our friend group has. In my personal data, I have a list of the greatest movies I've found, and I want to know if that movie is among them. I'm curious to know if I've already watched it and what the review scores are from both reference sites I use in my data. The same friend also recommended a game with a 64 in its name, and it was amazing.
---
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. |
| `/slack` | Your Slack workspace, read-only. |
| `/airtable` | Your Airtable bases, read-only. |
| `/tmp` | Scratch space, in memory. |
## `/slack`
```
/slack/
channels/
<channel-name>__<channel-id>/
<yyyy-mm-dd>/
chat.jsonl
files/
<name>__<file-id>
dms/
<user-name>__<dm-id>/
<yyyy-mm-dd>/
chat.jsonl
files/
<name>__<file-id>
users/
<username>__<user-id>.json
```
- `chat.jsonl`: one Slack message per line, `{type: str, user: str, text:
str, ts: str, subtype?: str, files?: list[dict], reactions?: list[dict]}`
- `<user>.json`: `{id: str, name: str, real_name: str, deleted: bool,
is_bot: bool, profile: {display_name: str, email: str, real_name: str}}`
## `/airtable`
```
/airtable/
bases/
<base-name>__<base-id>/
base.json
<table-name>__<table-id>/
table.json
records.jsonl
views/
<view-name>__<view-id>.jsonl
```
A base, table or view name in a path is sanitized: spaces and characters
unsafe in a shell become `_`. `ls` a directory for the exact name rather
than building the path; the id after the last `__` is exact.
- `base.json`: `{base_id: str, base_name: str, permission_level: str,
tables: list[{table_id: str, table_name: str, primary_field_id: str}]}`
- `table.json`: `{table_id: str, table_name: str, base_id: str, description:
str | null, primary_field_id: str, fields: list[{field_id: str,
field_name: str, type: str, description: str | null, options: dict |
null}], views: list[{view_id: str, view_name: str, type: str}]}`
- `records.jsonl`: one record per line, `{record_id: str, created_time: str,
fields: {<field-name>: <value>}}`; an empty cell is absent
- `<view>.jsonl`: the records the view shows, in its order, as
`records.jsonl` writes them| 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. |
/slack | Your Slack workspace, read-only. |
/airtable | Your Airtable bases, read-only. |
/tmp | Scratch space, in memory. |
/slack
/slack/
channels/
<channel-name>__<channel-id>/
<yyyy-mm-dd>/
chat.jsonl
files/
<name>__<file-id>
dms/
<user-name>__<dm-id>/
<yyyy-mm-dd>/
chat.jsonl
files/
<name>__<file-id>
users/
<username>__<user-id>.jsonchat.jsonl: one Slack message per line, {type: str, user: str, text: str, ts: str, subtype?: str, files?: list[dict], reactions?: list[dict]}<user>.json: {id: str, name: str, real_name: str, deleted: bool, is_bot: bool, profile: {display_name: str, email: str, real_name: str}}/airtable
/airtable/
bases/
<base-name>__<base-id>/
base.json
<table-name>__<table-id>/
table.json
records.jsonl
views/
<view-name>__<view-id>.jsonlA base, table or view name in a path is sanitized: spaces and characters unsafe in a shell become _. ls a directory for the exact name rather than building the path; the id after the last __ is exact.
base.json: {base_id: str, base_name: str, permission_level: str, tables: list[{table_id: str, table_name: str, primary_field_id: str}]}table.json: {table_id: str, table_name: str, base_id: str, description: str | null, primary_field_id: str, fields: list[{field_id: str, field_name: str, type: str, description: str | null, options: dict | null}], views: list[{view_id: str, view_name: str, type: str}]}records.jsonl: one record per line, {record_id: str, created_time: str, fields: {<field-name>: <value>}}; an empty cell is absent<view>.jsonl: the records the view shows, in its order, as records.jsonl writes them---
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.
You can also use `gh` for GitHub.
## slack
Use `slack <command> '<JSON arguments>'`. Run `slack <command> --help` to
get more information.
```sh
slack channels-list '{"channel_types":"public_channel,private_channel"}'
slack conversations-history '{"channel_id":"CHANNEL_ID","limit":"1d"}'
```
| Command | Arguments | Description |
|---|---|---|
| `slack channels-list` | `{channel_types: str, cursor?: str, limit?: number = 100, sort?: str}` | Get list of channels |
| `slack conversations-add-message` | `{channel_id: str, content_type?: str = "text/markdown", payload?: str, thread_ts?: str}` | Add a message to a public channel, private channel, or direct message (DM, or IM) conversation by channel_id and thread_ts. |
| `slack conversations-history` | `{channel_id: str, cursor?: str, include_activity_messages?: bool = false, limit?: str = "1d"}` | Get messages from the channel (or DM) by channel_id, the last row/column in the response is used as 'cursor' parameter for pagination if not empty |
## airtable
Use `airtable <command> '<JSON arguments>'`. Run `airtable <command> --help`
to get more information.
```sh
airtable list-bases '{}'
airtable list-tables '{"base_id":"BASE_ID"}'
airtable list-records '{"base_id":"BASE_ID","table_name":"TABLE","max_records":10}'
airtable search-records '{"base_id":"BASE_ID","table_name":"TABLE","field_name":"FIELD","value":"VALUE"}'
```
| Command | Arguments | Description |
|---|---|---|
| `airtable list-bases` | `{}` | List all accessible Airtable bases |
| `airtable list-tables` | `{base_id: str}` | List all tables in a base |
| `airtable list-records` | `{base_id: str, table_name: str, max_records?: number}` | List records in a table |
| `airtable search-records` | `{base_id: str, table_name: str, field_name: str, value: str}` | Search for records in a table |
## exa
Use `exa <command> '<JSON arguments>'`. Run `exa <command> --help` to get
more information.
```sh
exa web-search-exa '{"query":"QUERY","numResults":5}'
```
| Command | Arguments | Description |
|---|---|---|
| `exa web-search-exa` | `{query: str, numResults?: number}` | Search the web for any topic and get clean, ready-to-use content. |
## 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.| 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 jqwith 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.
You can also use gh for GitHub.
slack
Use slack <command> '<JSON arguments>'. Run slack <command> --help to get more information.
slack channels-list '{"channel_types":"public_channel,private_channel"}'
slack conversations-history '{"channel_id":"CHANNEL_ID","limit":"1d"}'| Command | Arguments | Description |
|---|---|---|
slack channels-list | {channel_types: str, cursor?: str, limit?: number = 100, sort?: str} | Get list of channels |
slack conversations-add-message | {channel_id: str, content_type?: str = "text/markdown", payload?: str, thread_ts?: str} | Add a message to a public channel, private channel, or direct message (DM, or IM) conversation by channel_id and thread_ts. |
slack conversations-history | {channel_id: str, cursor?: str, include_activity_messages?: bool = false, limit?: str = "1d"} | Get messages from the channel (or DM) by channel_id, the last row/column in the response is used as 'cursor' parameter for pagination if not empty |
airtable
Use airtable <command> '<JSON arguments>'. Run airtable <command> --help to get more information.
airtable list-bases '{}'
airtable list-tables '{"base_id":"BASE_ID"}'
airtable list-records '{"base_id":"BASE_ID","table_name":"TABLE","max_records":10}'
airtable search-records '{"base_id":"BASE_ID","table_name":"TABLE","field_name":"FIELD","value":"VALUE"}'| Command | Arguments | Description |
|---|---|---|
airtable list-bases | {} | List all accessible Airtable bases |
airtable list-tables | {base_id: str} | List all tables in a base |
airtable list-records | {base_id: str, table_name: str, max_records?: number} | List records in a table |
airtable search-records | {base_id: str, table_name: str, field_name: str, value: str} | Search for records in a table |
exa
Use exa <command> '<JSON arguments>'. Run exa <command> --help to get more information.
exa web-search-exa '{"query":"QUERY","numResults":5}'| Command | Arguments | Description |
|---|---|---|
exa web-search-exa | {query: str, numResults?: number} | Search the web for any topic and get clean, ready-to-use content. |
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.
| Model | VFS | MCP | VFS Tokens | MCP Tokens | Token Reduction Rate |
|---|---|---|---|---|---|
| Claude Opus 5.5 | 1/1 | 1/1 | 20.7k | 30.9k | 33% |
| GPT-6.1 Sol | 1/1 | 1/1 | 14.6k | 16.7k | 12% |
| GPT-5.6 Luna | 1/1 | 1/1 | 107k | 15.5k | −591% |
| Claude Haiku 5.5 | 1/1 | 1/1 | 110k | 99.1k | −11% |
| Gemini 3.8 Flash | 1/1 | 1/1 | 102k | 23.7k | −330% |