Kyvvu

Policy pack · Developer

Claude Code safety policy pack

Default safety manifest for Claude Code agents. Every policy addresses a real risk that developers face when using autonomous coding agents: credential exfiltration, destructive commands, scope escape, runaway and runaway loops.

What's in it

13 policies, 13 of them blocking.

Critical policies block the step before it runs. High, medium and low ones let it run and open an incident.

PolicyCheckedSeverityRule
No exec after secret readBefore every stepcriticaltainted_path_block
No network after secret readBefore every stepcriticaltainted_path_block
No force pushBefore every stepcriticalnot
No recursive delete of rootBefore every stepcriticalnot
No recursive delete of homeBefore every stepcriticalnot
No recursive delete via parent traversalBefore every stepcriticalnot
No recursive delete of system directoriesBefore every stepcriticalnot
No git reset --hardBefore every stepcriticalnot
No write outside projectBefore every stepcriticalall_of
No shell write to sensitive pathsBefore every stepcriticalnot
No shell read of secret filesBefore every stepcriticalnot
Max exec per taskBefore every stepcriticalexecution_max_steps
Max consecutive execBefore every stepcriticalmax_consecutive_same_type

Version 1.0.5. Source: manifests/developer/claude-code-safety.yaml.

Assign it

One command, no redeploy.

Assign it from the dashboard or the CLI. Running agents pick up an assignment within the policy refresh window, five minutes by default.

Policies
13, of which 13 are checked before every step.
Version
1.0.5
$ kyvvu list-manifests$ kyvvu assign-manifest --agent-id <agent> --repo-id <repo> \    --manifest manifests/developer/claude-code-safety.yaml

About this pack

All runtime policies are severity: critical (= block). These are genuinely dangerous actions where "warn but allow" makes no sense. Teams can downgrade individual policies to high (= warn) if they prefer softer enforcement.

Designed for agents registered via kyvvu-claude. Assign via the Kyvvu dashboard or API.

Runtime policies in this pack

From Kyvvu's open policy library at github.com/Kyvvu/manifests, Apache 2.0.

Next

Run the whole pack in your browser.

In your browser

Try it in the playground

The policy is loaded. Add the steps your agent takes and watch the engine decide, step by step.

On your machine

Five minutes, no account

kyvvu try runs a demo agent against the bundled baseline. Then assign this pack from the dashboard or the CLI.

For security teams

See it on your agents

A 30-minute demo on the agents you actually run, with the policies that fit them.