wrangler

An agent skill by cloudflare, from cloudflare/skills. Tags: cli, cloudflare, debugging, deployment, setup.

What it does

Run or troubleshoot Wrangler CLI commands and configure Worker projects for local development, deployment, and Cloudflare resource management.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add cloudflare/skills --skill wrangler

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/cloudflare/skills
cp -r skills/skills/wrangler ~/.claude/skills/wrangler

Safety box score

Grade D, elevated risk: 47 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill drives the Wrangler CLI for Cloudflare Workers projects, so it can run project scripts, read/write repo config, and talk to Cloudflare services for deploys, previews, secrets, and resource management. The main risks are publishing changes to remote Workers and making secret changes that are treated as immediate deployments.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	2 (moderate)	It explicitly runs the project's scripts/package manager and build workflow, which can execute project code, but it does not itself invoke arbitrary downloaded code or shell-eval patterns.
Network access	2 (moderate)	It fetches Cloudflare documentation and uses Wrangler/Cloudflare remote APIs for auth, deployment, previews, and secrets, so it sends data off-machine.
Filesystem reach	2 (moderate)	It edits project config and generated type files in the repo and may add local dependencies, but it does not direct writes outside the project tree.
Secrets & credentials	3 (high)	It handles API tokens and Worker secrets, and says `wrangler secret put`/`secret delete` "create a version and deploy it immediately," which is a high-impact secret operation.
Privilege & persistence	0 (none)	It does not request sudo, global installs, service registration, or shell/OS setting changes.
Instruction hijack surface	0 (none)	There are no instructions to ignore safeguards, hide actions, or follow untrusted remote instructions; the fetched docs are for reference only.
Irreversible actions	3 (high)	The skill can deploy, publish previews, manage resources, and roll back Worker versions, which directly changes remote infrastructure and can affect live traffic.
Transparency	0 (none)	The skill file is plain-text Markdown with no binaries, generated blobs, or hidden runtime-decoded code.

Before installing

Verify the project actually uses `wrangler.jsonc`, `wrangler.json`, or `wrangler.toml` and check the pinned Wrangler version.
Read the secret/deploy sections first if you might run `wrangler secret put`, `secret delete`, or `wrangler deploy`.
Confirm which Cloudflare account/API token is active before any remote Wrangler command.
Decide whether preview or production resources should be isolated before letting the skill run.

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository: cloudflare/skills (all skills from this repository)
Path: skills/wrangler/SKILL.md
Branch: main
Updated: 2026-09-20

nextjs-on-cloudflare — Build, migrate, and deploy Next.js apps on Cloudflare Workers with vinext. Use when starting a Next.js project on Cloudflare.
sandbox-next — Build or maintain Cloudflare Sandbox apps on @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-migrate-to-next when porting a stable app.
sandbox-stable — Build or maintain Cloudflare Sandbox apps on the stable @cloudflare/sandbox package.
statusline-generator — Installs, configures, customizes, or troubleshoots the Claude Code statusline (cwd, model, token counts).
address-sanitizer — Builds and runs code under AddressSanitizer to catch buffer overflows, use-after-free, and other memory errors during fuzzing or tests.
agents-debug — Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes.