setup

A setup check for the Cloudflare command-line tool and its credentials. Cloudflare provides web infrastructure and hosting services.

In plain words
What is it for?
Use it to verify the `cf` command, display its version, and check whether the expected Cloudflare credential settings exist.
Why use it?
It confirms that the command-line tool is installed and that required credential names are configured without exposing secret values.

Command

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.

agentmods
npx agentmods add commands/thrownlemon/claude-code-plugins/setup
Clone the repo
git clone --depth 1 https://github.com/ThrownLemon/claude-code-plugins
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 620 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00006 $0.00620
Opus 5 $0.00003 $0.00310
Sonnet 5 $0.00001 $0.00124
Haiku 4.5 $0.00001 $0.00062

Measured yesterday against content hash 782b56780c9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup scanned grade A with 0 findings 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 yesterday.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/cloudflare/commands/setup.md · 51 lines

What it actually says

You are verifying that the Cloudflare plugin environment is correctly set up.

Run the following checks:

  1. Check cf CLI installation:

    • Run which cf or check if cf command exists
    • If not found, inform the user: "The cf CLI is not installed or not in your PATH. Please install it from github.com/ThrownLemon/cloudflare-cli"
    • If found, display the version by running cf --version
  2. Check credentials configuration (without printing secrets):

    • Confirm ~/.cloudflare/.env exists: [ -f ~/.cloudflare/.env ] && echo present || echo missing
    • Confirm the required variable names are present without revealing values:
      for k in CLOUDFLARE_API_TOKEN CF_API_KEY CF_API_EMAIL CF_ACCOUNT_ID; do
        grep -q "^${k}=" ~/.cloudflare/.env 2>/dev/null && echo "$k: set in .env" || echo "$k: not in .env"
      done
      
    • Optionally check whether the variables are in the process environment ([ -n "$CLOUDFLARE_API_TOKEN" ] etc.) — again without echoing their values.
    • Never cat the .env file or print its values. Only report whether each key name exists.
    • Recommended credential path — scoped API Token: Set CLOUDFLARE_API_TOKEN to a token created at dash.cloudflare.com → My Profile → API Tokens. Scoped tokens grant only the permissions they need and can be revoked without rotating your global account. The legacy CF_API_KEY + CF_API_EMAIL pair (Global API Key) gives full account access — avoid it for new setups. CF_ACCOUNT_ID is only required by commands that target account-level resources; it is optional for zone-scoped operations.
    • If neither source has the required variables, instruct the user: "Cloudflare credentials not found. Add CLOUDFLARE_API_TOKEN=<your-scoped-token> to ~/.cloudflare/.env. If your cf CLI version requires the legacy keys, also add CF_API_KEY and CF_API_EMAIL, but prefer the token path."
  3. Test API connectivity:

    • Run cf zones list --json to verify credentials work
    • If successful, display: "✓ API connectivity verified"
    • If failed, display the error and suggest checking credentials
  4. Generate a status summary:

    Cloudflare Plugin Setup Status:
    
    cf CLI: [installed/not installed]
    Version: [version if available]
    Credentials: [configured/missing]
    API Connectivity: [working/failed]
    
    Zones accessible: [count of zones]
    

If any checks fail, provide clear instructions on how to fix the issue.

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.

  1. yesterday First seen · 51 lines · 6 tokens per session scan A 782b56780c9b

Subscribe to this mod's changes

setup is a command published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 6 tokens to every session and 620 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.