Wrangler CLI Skill

Publisher: Cloudflare plugin in openai/plugins · Editorial profile by AI Tools Ratings · Review method

What task is this skill designed for?

Use it when a Worker needs a reproducible development and release setup. Make environment selection visible in every remote operation and verify which bindings are simulated locally.

What input and output should you expect?

Input: Existing worker code, wrangler configuration, intended environment, resource names and a list of secrets by name only.

Output: Configuration changes, generated-binding guidance and a staged command plan with validation and rollback considerations. Review account and target names before any deploy.

What does it need to run?

Node tooling and a compatible Wrangler version. The source targets Wrangler 4 or later; check installed CLI help and schema before applying commands.

Published in the OpenAI Codex plugins repository. Compatibility evidence is the plugin package and its source instructions; this is not a claim of identical behavior in other agent clients.

How should you approach installation?

1. Open the pinned source and review the complete skill folder, including referenced helpers and license, before enabling it.
2. Use the corresponding plugin in a compatible Codex environment; preserve the skill folder structure rather than copying only SKILL.md. Confirm current plugin availability in your client.
3. Start with a disposable project and the trial prompt below. Grant only the stated access, inspect the proposed diff, and require separate approval for remote writes or publishing.

Installation guide: discovery, dependencies and runtime checks

What files, accounts or data can it access?

It can edit configuration and invoke a CLI. Authenticated commands can deploy, create or delete remote resources. Logs may contain user data; inspect permissions before granting live access.

What does the skill cost?

The skill itself is source guidance. Deployments and remote bindings use the account billing model; local development can still call paid external APIs if configured.

What are its limits and alternatives?

A dry-run checks packaging but cannot prove live routing or permission behavior. Local bindings do not establish production data safety, and remote AI bindings can incur costs during development.

Use provider documentation directly for a single command; use the platform skill when the service choice is still uncertain.

What could you ask in a small trial?

Try this with a small sample:

Audit this worker configuration for staging isolation. Show the exact target for each command, list remote bindings, and propose a dry-run sequence. Do not deploy, delete resources or read secret values.

How would you verify the result?

1. Staging and production resource IDs are distinct where required.
2. No secret values enter configuration or output.
3. Build and type checks are defined before deployment.
4. Rollback identifies the previous working artifact and resource dependencies.

Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.

Which source and license were checked?

Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder

Repository and current publisher guidance

Checked: 2026-10-30

Apache-2.0 License evidence

Report an error, license concern or request a new review.