A command for clearing Cloudflare’s cache for every URL in a zone or for selected URLs. Cloudflare’s cache is the edge storage that serves saved copies of website content closer to visitors.

Use it to purge all cached content for a Cloudflare zone or purge specific website URLs after an update.

It removes stale cached content when the live website has changed. Because clearing the cache immediately affects what users receive, the workflow requires safety checks and confirmation.

purge — Command for Claude Code by ThrownLemon/claude-code-plugins

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/ThrownLemon/claude-code-plugins

Made for: Claude Code.

Or install cloudflare, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/thrownlemon/claude-code-plugins/purge/github.svg)](https://agentmods.dev/commands/thrownlemon/claude-code-plugins/purge)

Your own site

<a href="https://agentmods.dev/commands/thrownlemon/claude-code-plugins/purge"><img src="https://agentmods.dev/badge/commands/thrownlemon/claude-code-plugins/purge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/thrownlemon/claude-code-plugins/purge"><img src="https://agentmods.dev/badge/commands/thrownlemon/claude-code-plugins/purge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 657 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00011	$0.00657
Opus 5.5	$0.00004	$0.00263
Sonnet 5.5	$0.00002	$0.00131
Haiku 4.5	$0.00001	$0.00066

Measured 1mo ago against content hash d21219084da0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

purge scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. **Reject dangerous tokens.** If a value contains `$(`, backticks, `;`, `|`, `&`, `>`, `<`, or starts with `-` (could be mistaken for a flag), refuse and ask the user to rephrase. **Double-quoting does NOT block comman

plugins/cloudflare/commands/purge.md · 49 lines

What it actually says

Input Safety — apply before any Bash invocation

Treat every $ARGUMENTS.* value as untrusted input. Before passing any value to the Bash tool:

Reject dangerous tokens. If a value contains $(, backticks, ;, |, &, >, <, or starts with - (could be mistaken for a flag), refuse and ask the user to rephrase. Double-quoting does NOT block command substitution — "$(rm -rf /)" still executes inside double quotes.
Prefer the Bash tool's argv contract over constructed shell strings. When you must use a shell string, single-quote the value and escape embedded single quotes ('\''), or build the command via printf %q.
Any "$ARGUMENTS.foo" patterns shown below are illustrative. Sanitize the value first; never blindly substitute.

You are purging Cloudflare cache for a zone. This is a destructive operation that will immediately affect users serving content from the edge.

ALWAYS confirm with the user before purging.

Quote every user-supplied value when shelling out. Always wrap $ARGUMENTS.zone and $ARGUMENTS.url in double quotes so shell metacharacters (&, ;, $(), etc.) cannot execute.

First, verify the zone exists by running cf zones get "$ARGUMENTS.zone" --json. If the zone doesn't exist, inform the user.

Then, based on the parameters:

If $ARGUMENTS.url is provided (purge specific URLs):

Parse the comma-separated URLs
Display what will be purged: "I will purge cache for these URLs: "
Ask for confirmation: "Are you sure you want to proceed? (yes/no)"
Only proceed if user confirms with "yes" or "y"
Run cf zones purge "$ARGUMENTS.zone" "$ARGUMENTS.url" --json
Display purged URLs and confirmation

If $ARGUMENTS.url is not provided (purge entire cache):

Display a strong warning: "⚠️ WARNING: This will purge the ENTIRE cache for zone $ARGUMENTS.zone. All cached content will need to be re-fetched from origin."
Ask for confirmation: "Type 'yes' to confirm you want to purge the entire cache for $ARGUMENTS.zone:"
Only proceed if user confirms with exactly "yes"
Run cf zones purge "$ARGUMENTS.zone" --json
Display confirmation that entire cache was purged

After successful purge, remind the user: "Cache has been purged. It may take a few moments for changes to propagate across all edge locations."

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 49 lines · 11 tokens per session scan C d21219084da0

Subscribe to this mod's changes

purge is a command published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 657 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Cloud DevOps and cloud

cost-optimize

Reduce cloud costs across AWS, Azure, and GCP through rightsizing, reserved and spot capacity, storage tuning, and cost monitoring.

wshobson/agents · 26 tokens

deploy

Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.

butterbase-ai/butterbase-skills · 20 tokens

env

Manage Vercel environment variables. Commands include list, pull, add, remove, and diff. Use to sync environment variables between Vercel and your local development environment.

vercel/vercel-plugin · 35 tokens

firebase-publish

Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.

Pierry/harness-kit · 20 tokens

scan

Scan AWS account for cost optimization.

prajapatimehul/claude-aws-cost-saver · 6 tokens

finops-status

Orientation — say where an opportunity or assignment sits in the five-step FinOps lifecycle and what unlocks next. Useful when a record has no active stage: an opportunity while its assignments do the work, an assignment whose plan has not been approved yet, or a rejected or archived assignment. Read-only; mutates…

glassity/agent-skills · 64 tokens

purge