Builtin policies - Failproof AI

Builtin policies cover secret handling, environment files, destructive shell commands, protected branches, cloud and infrastructure tools, package publishing, repeated calls, and end-of-task workflow checks.

Enable and verify a builtin policy

Dashboard
CLI

Install the policy on a connected machine with the local CLI.
Run a safe test action in the instrumented agent.
Go to Observe → policy and filter by the policy name, machine environment, or decision.
Open the linked session to confirm the matched tool input and returned reason.

failproofai policies
failproofai policy add block-rm-rf --cli claude --scope project
failproofai config --status

Remove it with failproofai policy remove block-rm-rf --cli claude --scope project.

List the policies available in your installed version:

failproofai policies

Enable one policy for a project:

failproofai policy add block-rm-rf --scope project

Enable several policies for selected harnesses:

failproofai policies --install block-sudo block-force-push \
  --cli claude codex --scope project

Some policies accept parameters or are marked beta. Review the description, match scope, and default behavior before rollout. A policy that protects one workflow may block valid operations in another.

Browse the complete builtin catalog

Review all 40 current policies, their triggers, recommended baseline, and parameters.

Prefer project scope for repository-specific expectations and user scope for machine-wide safety requirements.

​Enable and verify a builtin policy

Browse the complete builtin catalog

Enable and verify a builtin policy