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 rules/jdevalk/seo-graph/cursorrulesgit clone --depth 1 https://github.com/jdevalk/seo-graphWhat 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 | $0.00038 | $0.00038 |
| Opus 5 | $0.00019 | $0.00019 |
| Sonnet 5 | $0.00008 | $0.00008 |
| Haiku 4.5 | $0.00004 | $0.00004 |
Grade A, and why
cursorrules 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 yesterday.
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.
What it actually says
Read AGENTS.md for the complete API reference, site type recipes, and integration guide. It covers every piece builder, every common site type, and how to wire entities together.
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.
- yesterday First seen · 2 lines · 38 tokens per session scan A bad0226ca608
cursorrules is a cursor rule published in the GitHub repository jdevalk/seo-graph (48 stars, last pushed 15d ago), licensed MIT. It adds 38 tokens to every session, about $0.0002 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
astro-strapi-loader
Strapi 5 + @sensinum/astro-strapi-loader — content.config.ts, populate, qs, locales.
cursorrules
As an AI agent operating in this repository, you MUST execute the following state check before analyzing, coding, or responding to any user prompt.
case-uco-sdk
CASE/UCO SDK usage patterns for building digital forensics investigation graphs.
extension-authoring
Guidance for authoring CASE/UCO extension ontologies per the CDO Community Playground Guide.
testing
Rules for writing Jest tests in TypeScript.
astro-strapi-starter
Astro x Strapi starter — layout, content collections, block renderer vs StrapiBlocks, types.