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.
git clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/rules/d-padmanabhan/agent-engineering-handbook/405-cloudflare-waf-rules)<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/405-cloudflare-waf-rules"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/405-cloudflare-waf-rules.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 | $0.00123 | $0.07787 |
| Opus 5 | $0.00062 | $0.03893 |
| Sonnet 5 | $0.00025 | $0.01557 |
| Haiku 4.5 | $0.00012 | $0.00779 |
Grade A, and why
405-cloudflare-waf-rules 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 8d 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 — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare WAF Rules (Custom + Managed-Exception)
Audience: anyone authoring or reviewing a Cloudflare WAF rule, regardless of interface:
- Terraform (
cloudflare_rulesetresource) - HCL committed to a repo, applied viaterraform apply/ CI. - Cloudflare Dashboard - UI clicks under Security → WAF → Custom rules or Managed rules → Exceptions.
- Rulesets API - direct JSON
PUT/POSTagainsthttps://api.cloudflare.com/client/v4/zones/<zone_id>/rulesets/....
The rule covers both phases:
- phase
http_request_firewall_custom(custom rules) - actions likeblock,challenge,managed_challenge,js_challenge,log,skip. These are your policy. - phase
http_request_firewall_managed(managed-rule exceptions) - actionskiponly, bypassing OWASP / Cloudflare-managed signatures. Every one of these is a deliberate hole.
Relationship to 400-cloudflare.mdc: 400 is the broad Cloudflare platform playbook (Workers, Access, AOP, OWASP managed-ruleset configuration with PL1 + anomaly score threshold 60, the policy-level managed-rule exception discipline). This file is the tactical playbook you load when actually authoring the rule - in HCL, in the UI, or as a JSON payload. Use both together.
Why this rule exists: A loose predicate, a missing guard, or a name that hides intent ships the same risk regardless of authoring path - blocking legitimate traffic (custom rule bug) or silently bypassing managed signatures (skip rule bug). The substance (predicates, guards, naming, anti-patterns) is interface-independent; only the delivery mechanics differ (HCL vs UI vs JSON) and the change-management mechanics differ (Git PR vs change ticket + audit log vs API call + recorded runbook entry). This rule encodes the patterns observed in past WAF PR reviews that have shipped clean, and the failure modes that have shown up repeatedly.
[!IMPORTANT] The pre-edit gate, path predicate matrix, multi-value header syntax requirements, source-of-truth rule, naming convention, required guards, and most anti-patterns apply regardless of interface. The provenance and reviewer sections call out per-interface differences explicitly.
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.
- 8d ago First seen · 368 lines · 123 tokens per session scan A fbc92467b0c3
405-cloudflare-waf-rules is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 7,787 once invoked, about $0.0006 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 2026-08-30.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.