The Lint Runner Tool
Run the project’s linters and return violations with file and line — so an agent’s changes meet your standards before a human ever sees them, and reviews stay focused on substance.
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.
Read-only agents
Suggestions still require a human to run, test, and commit everything.
Unsafe execution
Running agent-generated code on real infrastructure is a security risk.
No verification
Without tests and builds, an agent can’t know its change works.
Ungoverned Git
Direct repo access with no policy or audit is a non-starter in the enterprise.
Lint Runner, without the risk
Capability
What it does
Check code style and catch issues before review.
it runs the project’s linters and returns style and quality violations with locations.
Assignable to any agent
How it works
Predictable, inspectable behavior
Designed to be reliable.
it detects or accepts the lint command and parses the output into structured findings, so an agent can auto-fix or address issues before opening a pull request.
Every call logged
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.
Per-tenant, logged
Parameters
The lint_runner tool accepts these inputs when an agent calls it. Required inputs are flagged.
default: . Optional Project directory.
default: false Optional Apply auto-fixes where the linter supports them.
Where Lint Runner pays back
Standards
Ensure changes match the team’s style.
Auto-fix
Let the agent clean up trivial issues automatically.
Cleaner PRs
Keep review focused on logic, not formatting.
Quality gates
Block code that fails lint from merging.
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.
What changes after you assign it
Questions about the Lint Runner tool
What is the Lint Runner tool?
It runs the project’s linters and returns style and quality violations with locations. 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 it fix issues automatically?
Yes. Set fix to true to apply the linter’s auto-fixes where supported.
What does it return?
Structured violations with file and line so an agent can address each one.
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.
Tools that work well alongside this one
Where this tool delivers value
Put Lint Runner to work
See the Lint Runner tool assigned to an agent and orchestrated in a governed, on-premise network.