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/sim-xia/blind-auditor/cursorrulesgit clone --depth 1 https://github.com/Sim-xia/Blind-AuditorWhat 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 | $0.00144 | $0.00144 |
| Opus 5 | $0.00072 | $0.00072 |
| Sonnet 5 | $0.00029 | $0.00029 |
| Haiku 4.5 | $0.00014 | $0.00014 |
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
代码生成规则
CRITICAL INSTRUCTION: 每当你为用户生成代码时，你必须遵循以下流程：
- 内部生成代码（不要直接输出）
- 调用 MCP 工具
submit_draft，传入代码和语言参数 - 严格遵守工具返回的指令
示例流程：
- 如果返回审计指令，立即切换为审计员角色进行代码审查
- 如果返回修复指令，按要求修正代码并重新提交
- 如果返回放行指令，将最终代码展示给用户
重要: 此规则适用于所有代码生成请求，无例外。
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 · 16 lines · 144 tokens per session scan A fddcfaf1d4a5
cursorrules is a cursor rule published in the GitHub repository Sim-xia/Blind-Auditor (11 stars, last pushed 8mo ago), licensed MIT. It adds 144 tokens to every session, about $0.0007 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
cursorrules
An autonomous agent that conducts deep research on any data using any LLM providers.
startup
需要起的资源.
diplomat-reviewer
Reviews Python code for unguarded AI agent tool calls. Use when reviewing agent code, scanning for security issues, or checking tool call safety.
p8-enforcement
P8 Enforcement Rules — Injected into every Agent conversation.
local-brain-mcp-usage
local memory for AI agents.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.