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 skills add aAAaqwq/AGI-Super-Team --skill cloudflare-pagesgit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/aaaaqwq/agi-super-team/cloudflare-pages)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/cloudflare-pages"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/cloudflare-pages/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.
<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/cloudflare-pages"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/cloudflare-pages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.01661 |
| Opus 5 | $0.00047 | $0.00830 |
| Sonnet 5 | $0.00019 | $0.00332 |
| Haiku 4.5 | $0.00009 | $0.00166 |
Grade A, and why
cloudflare-pages 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare Pages
Deploy any static site to Cloudflare Pages — create projects, attach custom domains, wire up CI/CD, and verify deployments. Framework-agnostic: works with Hugo, Astro, Next.js, Nuxt, SvelteKit, or any build tool that produces static output.
Prerequisites
| Requirement | How to get it |
|---|---|
| wrangler CLI | npm i -g wrangler then wrangler login (opens browser OAuth) |
| Cloudflare account | dash.cloudflare.com — free tier works |
| Account ID | Dashboard → any zone → Overview sidebar, or wrangler whoami |
| API Token (CI/CD) | Dashboard → API Tokens → "Edit Cloudflare Workers" template (includes Pages) |
| DNS API Token | Dashboard → API Tokens → Custom → Zone:DNS:Edit (only if adding custom domains via API) |
| Zone ID | Dashboard → your domain → Overview sidebar (only for custom domains) |
Quick Deploy
For a one-off manual deploy when CI/CD isn't set up yet:
# 1. Build your site
<your-build-command> # e.g. hugo --minify, npm run build
# 2. Deploy output directory
wrangler pages deploy <output-dir> --project-name <project-name>
Each deploy gets a unique preview URL. The latest deploy on production branch becomes the live site at <project>.pages.dev.
Full Setup Workflow
Step 1 — Create the Pages project
bash scripts/setup-pages-project.sh <project-name> "<build-command>" <output-dir> [branch]
This runs wrangler pages project create and prints the resulting *.pages.dev URL. The branch argument defaults to main.
Manual alternative:
wrangler pages project create <project-name> --production-branch main
Step 2 — Deploy
Build and deploy:
<your-build-command>
wrangler pages deploy <output-dir> --project-name <project-name>
Step 3 — Add a custom domain
# Set required environment variables
export CLOUDFLARE_ACCOUNT_ID="<your-account-id>"
export CLOUDFLARE_API_TOKEN="<pages-edit-token>"
export CLOUDFLARE_ZONE_ID="<your-zone-id>"
export CLOUDFLARE_DNS_TOKEN="<dns-edit-token>" # optional, falls back to API_TOKEN
bash scripts/add-custom-domain.sh <custom-domain> <project-name>
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.
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 · 155 lines · 94 tokens per session scan A ab9ecd5a654d
cloudflare-pages is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,661 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 2026-09-05.
Other skills, from other repositories
costguard
Find and quantify CI/cron and cloud-spend waste. Audit repos, run read-only provider billing checks, preview or apply CI auto-fixes, and render a monthly cost digest.
choosing-deployment-strategy
Use when choosing deployment strategy within operations lifecycle boundaries, especially when does the artifact make the owned decision for choosing deployment strategy explicit and bounded?.
designing-ci-cd
Use when designing ci cd within operations lifecycle boundaries, especially when does the artifact make the owned decision for designing ci cd explicit and bounded?.
monitoring-post-release
Use when monitoring post release within operations lifecycle boundaries, especially when does the artifact make the owned decision for monitoring post release explicit and bounded?.
devops
Use when setting up CI/CD pipelines, deploying applications, managing cloud infrastructure (AWS, GCP, Azure), implementing monitoring, containerizing services, or automating deployments with infrastructure as code.
06-部署和运维
Chinese-language deployment and operations instructions for releasing software on platforms such as Cloud Run, Vercel, Cloudflare, Docker, and WeChat mini programs.