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/2019-02-18/mcx/cursorrulesgit clone --depth 1 https://github.com/2019-02-18/MCXWhat 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 | $0.00170 | $0.00170 |
| Opus 5 | $0.00085 | $0.00085 |
| Sonnet 5 | $0.00034 | $0.00034 |
| Haiku 4.5 | $0.00017 | $0.00017 |
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 2d 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.
What it actually says
MCP mcp-feedback-enhanced 规则
- 在任何流程、任务、对话进行时，无论是询问、回复、或完成阶段性任务，皆必须调用 MCP mcp-feedback-enhanced。
- 每当收到用户反馈，若反馈内容非空，必须再次调用 MCP mcp-feedback-enhanced，并根据反馈内容调整行为。
- 仅当用户明确表示「结束」或「不再需要交互」时，才可停止调用 MCP mcp-feedback-enhanced，流程才算结束。
- 除非收到结束指令，否则所有步骤都必须重复调用 MCP mcp-feedback-enhanced。
- 完成任务前，必须使用 MCP mcp-feedback-enhanced 工具向用户询问反馈。
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.
- 2d ago First seen · 7 lines · 170 tokens per session scan A d8e39ccd0527
cursorrules is a cursor rule published in the GitHub repository 2019-02-18/MCX (1 stars, last pushed 1y ago), licensed MIT. It adds 170 tokens to every session, about $0.0009 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 2026-08-31.
Other cursor rules, from other repositories
playwright
Playwright e2e guidelines distilled from PR.
real-browser-mcp
Instructions for using Real Browser MCP to control the user's actual browser.
invictum-browser
Use Invictum Browser Bridge whenever the user requests IBB, IBG, Invictum Browser Bridge, or Invictum Browser Gate.
rule_main
Core non-negotiable engineering checks.
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.