AGENTKIT/WORKS

pack · core tier

Agent Guardrail Pack

Seven controls that refuse the commands that deleted other people's work.

PRICE$79$49
Launching soon — get first-buyer pricing ↓

CHECKOUT OPENS AT LAUNCH · EARLY LIST GETS THE DISCOUNT

Your coding agent will eventually run something it should not. These are the seven commands it runs — each one derived from a documented incident where an agent destroyed a production database, a repository, or fifteen years of family photos. Installs as a PreToolUse hook that actually refuses, cites the incident it is protecting you from, and stays silent the rest of the time.

Why it's different

  • Refuses at the tool call — does not depend on the model choosing to comply
  • Three-way decisions: denies catastrophes, asks about ambiguity, stays silent otherwise
  • Every block cites its incident and links to the write-up
  • Python 3 stdlib only — nothing to install, nothing to trust

Questions, answered

Does this work with Cursor?+

Partly, and the honest answer matters here. Real enforcement needs a PreToolUse hook, which Claude Code has and Cursor does not. Cursor gets .cursorrules — the same seven rules as instructions the agent can ignore. If you are on Cursor you are buying documented rules, not enforcement.

Will it get in my way?+

It is silent on ordinary commands, and every control ships a test proving it permits normal work — `rm -rf node_modules`, `git push`, `prisma db push` against localhost. Ambiguous cases show a permission dialog rather than guessing.

Is this a sandbox?+

No, and do not treat it as one. It reads the command about to run, so it will not see a deletion inside a script the agent wrote and then executed. It raises the floor against the documented failure modes.

Add tool connectors

Workflow kits teach the job. Integration kits handle the tools. They stack.