Code Execution & Workspace Tool

The File List Tool

Enumerate the files and directories in the agent’s workspace, optionally filtered by glob, so an agent can understand a project’s structure before it reads or changes anything.

Explore VDF AI Agents
SandboxedRuns in an isolated workspace
GovernedEvery action logged
AssignableTo any engineering agent
100%On-premise capable
The Execution Gap

A suggestion isn’t a shipped change

An agent that can only propose code still leaves all the work to a human. To actually deliver, it needs a real, governed workspace where it can run code, edit files, test, and use Git — safely, and without touching anything you didn’t allow.

01

Read-only agents

Suggestions still require a human to run, test, and commit everything.

02

Unsafe execution

Running agent-generated code on real infrastructure is a security risk.

03

No verification

Without tests and builds, an agent can’t know its change works.

04

Ungoverned Git

Direct repo access with no policy or audit is a non-starter in the enterprise.

How the Tool Works

File List, without the risk

Capability

What it does

List files and folders in the workspace.

it lists the files and directories under a workspace path, optionally filtered by a glob pattern.

Tool
File List

Assignable to any agent

ListGlobStructureScoped

How it works

Predictable, inspectable behavior

Designed to be reliable.

listing is confined to the sandboxed workspace and logged, so an agent can map a project’s layout without reaching outside it.

Governed
Policy + Audit

Every call logged

ScopedLoggedGovernedOn-prem

Governance

Private, governed, on-premise

Runs inside your perimeter.

Execution runs in an isolated, on-premise sandbox scoped per tenant with full command and file audit logging, so an agent can do real work on your code without unsafe access or anything leaving your perimeter.

100%
On-Prem

Per-tenant, logged

On-premRBACAudit logSovereign
Inputs

Parameters

The file_list tool accepts these inputs when an agent calls it. Required inputs are flagged.

Name Type Required Description
path string
default: .
Optional Directory to list (workspace-relative).
glob string Optional Optional glob to filter results (e.g. **/*.ts).
recursive boolean
default: true
Optional Whether to recurse into subdirectories.
Where it pays back

Where File List pays back

Orientation

Map a repo’s structure before diving in.

Targeted work

Find all files of a type to operate on.

Discovery

Locate where a component or config lives.

Sanity checks

Confirm generated files landed where expected.

How VDF AI connects it

Assigned to agents, orchestrated as networks

On VDF AI, an industry’s use cases map to agents, and you assign tools like this one to those agents. Compose multiple agents into a governed, on-premise network.

ROI Snapshot

What changes after you assign it

Faster
From suggestion to shipped
Verified
Changes tested before merge
Traceable
Every command audited
100%
Code never leaves your perimeter
FAQ

Questions about the File List tool

What is the File List tool?

It lists the files and directories under a workspace path, optionally filtered by a glob pattern. Assigned to a VDF AI agent, it runs under role-based policy with full audit logging so the capability is safe to use in production.

Can I filter what it returns?

Yes. Pass a glob such as **/*.py to list only matching files.

Is it recursive?

By default yes; set recursive to false to list a single directory level.

Does it run on-premise?

Yes. Like every VDF AI tool, it can run on-premise or in your sovereign cloud, scoped per user and audit-logged, so your data never leaves your perimeter.

How do agents use it?

You assign the tool to an agent under a role-based policy; the agent calls it as one step in a task, and several agents and tools can be orchestrated together as a governed VDF AI Network.

Put File List to work

See the File List tool assigned to an agent and orchestrated in a governed, on-premise network.