blitzhash360-webblitzhash360-web/blitzhash-cloudflare-production-skills/AGENTS.md

blitzhash-cloudflare-production-skills

AGENTS.md0 starsChanged 9 days agoMITView on GitHub

Instructions for AI coding agents (Claude Code, Cursor, Codex, Windsurf, Copilot and others) working with this repo or using it to manage a user's Cloudflare account. Agent skills (skills/*/SKILL.md), Cursor rules (.cursor/rules/*.mdc, generated from the skills) and a zero-dependency Node CLI (bin/cf-skills.mjs, commands in scripts/) that calls the official Cloudflare API v4. cf-skills = node bin/cf-skills.mjs in a clone, or npx -y github:blitzhash360-web/blitzhash-cloudflare-production-skills.

Reads credentials

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository14 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/cloudflare-dns-records.mdcCursor rule
- .cursor/rules/cloudflare-rate-limiting.mdcCursor rule
- .cursor/rules/cloudflare-safety.mdcCursor rule
- .cursor/rules/cloudflare-turnstile.mdcCursor rule
- .cursor/rules/cloudflare-waf-rules.mdcCursor rule
- .cursor/rules/cloudflare-zone-audit.mdcCursor rule
- .cursor/rules/cloudflare-zones-overview.mdcCursor rule
- cloudflare-dns-recordsSkill
- cloudflare-rate-limitingSkill
- cloudflare-turnstileSkill
- cloudflare-waf-rulesSkill
- cloudflare-zone-auditSkill
- cloudflare-zones-overviewSkill

The file

We split this AGENTS.md into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Never delete records or rules the user did not name.
line 24
Very specific:
Run cf-skills audit before and after, and report the score change in plain English.
line 25
Very specific:
After editing a skill, run node scripts/build-cursor-rules.mjs to regenerate the Cursor rules.
line 31
Very specific:
Never add real zone IDs, account IDs, tokens or domains to fixtures.
line 32

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

AGENTS.md: BlitzHash Production Skills for Cloudflare

Instructions for AI coding agents (Claude Code, Cursor, Codex, Windsurf, Copilot and others) working with this repo or using it to manage a user's Cloudflare account.

What this repo is

Agent skills (skills/*/SKILL.md), Cursor rules (.cursor/rules/*.mdc, generated from the skills) and a zero-dependency Node CLI (bin/cf-skills.mjs, commands in scripts/) that calls the official Cloudflare API v4.

Task	Skill	Command
Is this domain secure? What do I fix first?	`skills/cloudflare-zone-audit`	`cf-skills audit`
Point a domain/subdomain at a host, edit DNS	`skills/cloudflare-dns-records`	`cf-skills dns ...`
Block attacks, protect admin, block countries	`skills/cloudflare-waf-rules`	`cf-skills waf ...`
Stop brute force / API abuse	`skills/cloudflare-rate-limiting`	`cf-skills ratelimit ...`
Stop form spam and bot signups	`skills/cloudflare-turnstile`	`cf-skills turnstile ...`
Which domains do I have, which nameservers	`skills/cloudflare-zones-overview`	`cf-skills zones ...`

cf-skills = node bin/cf-skills.mjs in a clone, or npx -y github:blitzhash360-web/blitzhash-cloudflare-production-skills.

Non-negotiable safety rules

The token comes only from CLOUDFLARE_API_TOKEN (env or git-ignored .env). Never ask the user to paste it in chat, never print it, never commit it. There is deliberately no --token flag.
Writes are dry runs until --apply. Show the printed plan to the user, wait for an explicit "yes", then re-run the same command with --apply --yes.
Never delete records or rules the user did not name. Never widen token permissions beyond docs/TOKEN-PERMISSIONS.md.
Run cf-skills audit before and after, and report the score change in plain English.
Zone settings (SSL mode, Always Use HTTPS, TLS, Bot Fight Mode, DNSSEC) are reported by the audit but not changed by these scripts; walk the user through the dashboard.

Working on the code

Node 18.17+, no dependencies. npm test runs the suite against a local mock Cloudflare API (test/mock-cloudflare.mjs); it never contacts Cloudflare.
After editing a skill, run node scripts/build-cursor-rules.mjs to regenerate the Cursor rules.
Never add real zone IDs, account IDs, tokens or domains to fixtures. Use .example domains and documentation IPs (203.0.113.0/24, 198.51.100.0/24).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free