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/graphprotocol/graph-toolingWrote 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/graphprotocol/graph-tooling/mdc)<a href="https://agentmods.dev/rules/graphprotocol/graph-tooling/mdc"><img src="https://agentmods.dev/badge/rules/graphprotocol/graph-tooling/mdc/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/rules/graphprotocol/graph-tooling/mdc"><img src="https://agentmods.dev/badge/rules/graphprotocol/graph-tooling/mdc.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01857 | $0.01857 |
| Opus 5.5 | $0.00743 | $0.00743 |
| Sonnet 5.5 | $0.00371 | $0.00371 |
| Haiku 4.5 | $0.00186 | $0.00186 |
Grade A, and why
mdc 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 1mo 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: Guidelines and best practices for creating .mdc (Markdown Configuration) files in Cursor, including structure, metadata annotations, and formatting rules globs: ["**/*.mdc"]
Cursor MDC File Guidelines
@context { "type": "documentation", "purpose": "cursor_rules", "format_version": "1.0.0", "supported_content_types": [ "guidelines", "api_docs", "examples", "implementations" ] }
@structure { "required_sections": [ "frontmatter", "title", "context", "content_sections" ], "optional_sections": [ "version", "last_updated", "examples", "implementations", "related_files" ], "recommended_sections": [ "practical_examples", "common_patterns", "type_definitions" ] }
File Structure
1. Frontmatter
@frontmatter_rules [ { "id": "position", "rule": "Must be at the very top of the file", "severity": "error" }, { "id": "description", "rule": "Single sentence, clear purpose", "severity": "error" }, { "id": "globs", "rule": "Array of relevant file patterns", "severity": "error" }, { "id": "related_docs", "rule": "Optional array of related documentation files - MUST only reference existing files", "severity": "error" }, { "id": "file_validation", "rule": "All referenced files must exist in the workspace", "severity": "error" } ]
Example frontmatter:
---
description: Guidelines for implementing feature X
globs: ["**/*.{ts,tsx}"]
related_docs: ["docs/architecture/feature-x.md"]
---
2. Metadata Annotations
@annotations { "syntax": "@annotation_name JSON_content", "placement": "Before relevant sections", "format": "Valid JSON with proper indentation", "types": { "context": "Project and document context", "rules": "List of rules or requirements", "format": "Format specifications", "options": "Available options", "examples": "Implementation examples", "implementations": "Full implementation details", "related": "Related documentation or code" } }
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.
- 1mo ago First seen · 355 lines · 1,857 tokens per session scan A 0301fbf8a4c9
mdc is a cursor rule published in the GitHub repository graphprotocol/graph-tooling (424 stars, last pushed today), licensed Apache-2.0. It adds 1,857 tokens to every session, about $0.0074 per session on Opus 5.5. 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 2026-09-01.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).