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.
npx agentmods add skills/goodsmileduck/claude-registry/cloudflare-cf-clinpx skills add Goodsmileduck/claude-registry --skill cloudflare-cf-cligit clone --depth 1 https://github.com/Goodsmileduck/claude-registryWrote 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.
[](https://agentmods.dev/skills/goodsmileduck/claude-registry/cloudflare-cf-cli)<a href="https://agentmods.dev/skills/goodsmileduck/claude-registry/cloudflare-cf-cli"><img src="https://agentmods.dev/badge/skills/goodsmileduck/claude-registry/cloudflare-cf-cli.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00101 | $0.02188 |
| Opus 5 | $0.00051 | $0.01094 |
| Sonnet 5 | $0.00020 | $0.00438 |
| Haiku 4.5 | $0.00010 | $0.00219 |
Grade A, and why
cloudflare-cf-cli scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Don't reach for `cf` in CI just because it's new. Reach for it when it shortens a script you'd otherwise write with curl + jq — and pin the version when you do. How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare cf CLI
cf is Cloudflare's new unified CLI, announced April 2026, intended to eventually become the next major version of Wrangler. It exposes ~3,000 API operations across 100+ products through one consistent command surface. This skill is about using it correctly while it is still a technical preview.
When to invoke
- The user mentions
cf,npx cf, or "the new Cloudflare CLI" / "CLI for all of Cloudflare". - A script or workflow is about to replace
wrangler ...withcf .... - An agent is generating
cfcommands and may not know the flag conventions. - A
cfinvocation behaved as if it targeted production when the user expected local. - The user is choosing between
cf,wrangler, direct REST, the officialcloudflareSDK, or Terraform.
Cross-cutting rules
cfis technical preview. Only a small subset of products is wired up. Conventions can shift between releases.wranglerstays authoritative for CI/CD untilcfreaches GA. Usecffor local exploration, ad-hoc agent work, and feedback. Ifcfmust be used in a script, pin the exact version — never unpinnednpx cfin CI.cfdefaults to the REMOTE resource. Without--local, every mutation hits production. See the local-vs-remote trap.- Token scoping rules are identical to the
cloudflare-dns-zonesskill — never the Global API Key, scope to minimum permissions on specific zones/accounts. Forcfadditionally: prefer a separate non-prod token for local work, so an accidental remote write fails 403 instead of corrupting production. - Don't guess flag names by analogy.
cfenforces consistent flags across the surface (--force,--json,--local). Verify withcf <command> --helprather than reaching for the synonym another CLI uses.
Verify current preview status before recommending: https://blog.cloudflare.com/cf-cli-local-explorer/. Training data ages fast on preview tools.
Don't confuse cf with neighbors
What ships with it
3 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.
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.
- 5d ago First seen · 129 lines · 101 tokens per session scan A 45f4283b9c2f
cloudflare-cf-cli is a skill published in the GitHub repository Goodsmileduck/claude-registry (1 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 2,188 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
implementing-infrastructure-as-code-security-scanning
This skill covers implementing automated security scanning for Infrastructure as Code (IaC) templates using tools like Checkov, tfsec, and KICS. It addresses detecting misconfigurations in Terraform, CloudFormation, Kubernetes manifests, and Helm charts before deployment, establishing policy-based governance, and…
hunt-cicd
Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pullrequesttarget Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log…
cloudbees_oc
CloudBees Operations Center integration for cross-controller deployment visibility and feature flag correlation during RCA.
alerting-irm
Configure Grafana Alerting, Incident Response Management (IRM), and SLOs end-to-end — provisions Grafana-managed and data-source-managed alert rules, contact points (Slack/PagerDuty/email/webhook), notification policies with hierarchical matchers, silences, mute timings, on-call schedules and escalation chains…
scheduled-jobs
Covers cron and scheduled work done right — idempotency, preventing overlapping runs, monitoring for missed and failed runs, alerting on silence, and getting time zones and DST transitions correct. Use this whenever the user is writing a cron job or Kubernetes CronJob, asks why a scheduled job ran twice or didn't run…
gitops
Establishes Git as the single source of truth for deployed state, with a pull-based controller reconciling the cluster to match a repo instead of humans or pipelines pushing changes via kubectl or helm. Use this whenever the user designs a deployment repo layout, asks how environments should be promoted, debates…