cloudflare-analytics

cloudflare-analytics is a skill for Claude Code from Goodsmileduck/claude-registry. It costs 97 tokens per session (1,093 once invoked), scanned A, original, MIT.

A guide for reading Cloudflare traffic and usage data through its GraphQL Analytics API. Cloudflare is a service that hosts, protects, and runs websites and web applications.

In plain words
What is it for?
Use it to inspect requests, visitors, bandwidth, cached and uncached traffic, Workers and Pages Functions usage, and real-user web analytics by hostname.
Why use it?
It provides account-specific traffic figures when the usual Cloudflare tools do not expose them, while checking data-retention and plan limits first.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the cloud-platform-skills plugin — 7 skills shipped together

Good fit Use it to inspect requests, visitors, bandwidth, cached and uncached traffic, Workers and Pages Functions usage, and real-user web analytics by hostname.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goodsmileduck/claude-registry/cloudflare-analytics
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.

Any agent
npx skills add Goodsmileduck/claude-registry --skill cloudflare-analytics
Clone the repo
git clone --depth 1 https://github.com/Goodsmileduck/claude-registry

Made for: Claude Code.

Or install cloud-platform-skills, the plugin that ships this one along with the rest of its 7 skills.

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.

agentmods badge for cloudflare-analytics

README.md
[![agentmods](https://agentmods.dev/badge/skills/goodsmileduck/claude-registry/cloudflare-analytics.svg)](https://agentmods.dev/skills/goodsmileduck/claude-registry/cloudflare-analytics)
Your own site
<a href="https://agentmods.dev/skills/goodsmileduck/claude-registry/cloudflare-analytics"><img src="https://agentmods.dev/badge/skills/goodsmileduck/claude-registry/cloudflare-analytics.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,093 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.01093
Opus 5 $0.00048 $0.00547
Sonnet 5 $0.00019 $0.00219
Haiku 4.5 $0.00010 $0.00109

Measured 7d ago against content hash 0675d690ace6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cloudflare-analytics 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 7d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/cf-host-traffic.sh, scripts/cf-limits.sh, scripts/cf-query.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/cloud-platform-skills/skills/cloudflare-analytics/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cloudflare Analytics

Cloudflare's MCP servers do not expose traffic analytics — the observability server covers Workers Logs only (and only when a Worker sets [observability] in its wrangler config), and Radar is public internet-wide data unrelated to any one account. Per-hostname numbers come from the GraphQL Analytics API, which these scripts wrap.

Setup

All scripts need CLOUDFLARE_API_TOKEN. Create at dash.cloudflare.com → My Profile → API Tokens → Custom token with Zone > Analytics > Read, Zone > Zone > Read, and Account > Account Analytics > Read.

Never let the user paste the token into the conversation — it lands in the transcript permanently. Ask them to run the command themselves (in Claude Code, prefixed with !), which returns only the output. If a token does end up in the transcript, say so plainly and tell them to rotate it.

Workflow

1. Probe limits first. Plan entitlements decide what is answerable, and they are not derivable from the docs — the published API capability is not the same as a given zone's grant.

scripts/cf-limits.sh <zone-name>

Returns maxDuration (widest single window) and notOlderThan (retention) per dataset. These are independent: 8-day retention with a 1-day max window means eight separate queries, not one.

2. Pick the dataset by whether you need a per-hostname breakdown. clientRequestHTTPHost exists only on httpRequestsAdaptiveGroups, which is the most range-restricted dataset. That tension drives most decisions here — see references/datasets.md.

3. Run.

scripts/cf-host-traffic.sh <zone> [YYYY-MM-DD]  # per-hostname table, 24h window
scripts/cf-query.sh <query-file> '<vars-json>'  # arbitrary query

cf-query.sh accepts - to read the query from stdin, prints raw JSON, and exits non-zero on GraphQL errors.

Non-obvious behavior

Errors arrive with HTTP 200. A failed query returns status 200 with an errors array. Always inspect body.errors; both scripts do.

Read the full file on GitHub · 98 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 98 lines · 97 tokens per session scan A 0675d690ace6

Subscribe to this mod's changes

cloudflare-analytics is a skill published in the GitHub repository Goodsmileduck/claude-registry (1 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 1,093 once invoked, about $0.0005 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.