Loading…
Execution pattern
Prevent destructive production changes
Make deleting production a decision, not a command.
What executes
A command, script, or agent drops a table, deletes a bucket, or tears down infrastructure.
What normally goes wrong
The destructive command is indistinguishable from a routine one until it has run. An agent given shell access holds every credential needed to be catastrophic without holding any intent to be.
The decision
The signals available at the moment of the action, and the rule that judges them.
Signals
- Whether the target is production
- Reversibility of the operation
- Whether a backup exists and is recent
- Actor's authority for destructive operations
The gate
Refuse irreversible operations against production unless a human with destructive authority has approved this specific action.
ALLOW
The operation proceeds under recorded authority.
ESCALATE
The operation waits on someone who holds destructive authority.
BLOCK
The operation does not run; the dossier records what would have been destroyed.
Four stages left to right. Input signals — user or agent identity, context and data, tools and resources, spend and budget, policies, history and reputation, and environment — enter the Decionis Protocol. Inside, the protocol normalizes context and intent, evaluates policies and rules, runs a deterministic risk and policy engine, and explains the reason and evidence. It emits a verdict: ALLOW (authorized), ESCALATE (needs approval or more info), or BLOCK (high risk or out of policy). The verdict drives an enforcement action: allow, block, require approval, or throttle and limit. Every decision is recorded for audit, learning, and continuous improvement.
3 policies implement this pattern
Fork one and change the thresholds. Available today on 2 platforms.
Claude Code Destructive-Shell Gate
Never let an agent run `rm -rf`, a force-drop, or a disk-level command without a human approval on the tool call.
claude code
Codex Blast-Radius Gate
Scores every Codex tool call by blast radius and escalates anything that could touch production before it runs.
codex
Claude Code Migration & Infra Gate
Holds agent-authored database migrations and `terraform apply` runs until a human signs the blast radius.
claude code
Related concepts
This pattern is one answer to each of these.
What to do next
The same five steps for every pattern in the library.
- Simulate this recipe
Run the policy against a realistic action in the browser. Push it past what the rules allow and watch the verdict come back. No account.
- View the signed Decision Dossier
See exactly what was decided and why: the rule that fired, the evidence it read, the policy version in force, and an Ed25519 signature you can verify yourself.
- Deploy in shadow mode
Measure what the policy would have caught on your own traffic without touching the live path. Every recipe defaults to shadow, so the first deployment carries no execution risk.
- Connect a real workflow
Point the same policy at the system where the action actually originates — a checkout, an ERP posting, a Zap, an agent's tool call.
- Share the verified result
Publish the proof: a public verification link, an embeddable badge, a PR comment, or an anonymized shadow-mode finding. This is how the next person discovers Decionis.