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/fbrbovic/cursor-rule-framework/cursor-rules-managementgit clone --depth 1 https://github.com/fbrbovic/cursor-rule-frameworkWhat 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 | $0.00029 | $0.01356 |
| Opus 5 | $0.00015 | $0.00678 |
| Sonnet 5 | $0.00006 | $0.00271 |
| Haiku 4.5 | $0.00003 | $0.00136 |
Grade A, and why
cursor-rules-management 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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🚨 CRITICAL: Cursor Rules Management Policy 🚨
This rule ensures proper location, format, and handling of all Cursor MDC rule files.
PART 1: MANDATORY LOCATION POLICY
All Cursor Rules Must Live in .cursor/rules/
This is the ONLY acceptable location for cursor rules files (.mdc).
✅ Correct Locations
- ✅
.cursor/rules/rules.mdc - ✅
.cursor/rules/architecture.mdc - ✅
.cursor/rules/any-other-rule.mdc
❌ INCORRECT Locations (NEVER USE)
- ❌
rules.mdc(root level) - ❌
migration.mdc(root level) - ❌
backend-encore/rules.mdc - ❌ Any other location outside
.cursor/rules/
Why Location Matters
- Cursor IDE Integration: Cursor only recognizes rules in
.cursor/rules/ - Team Consistency: All team members expect rules in standard location
- Version Control: Proper .gitignore handling for cursor-specific files
- Tool Compatibility: Other cursor-compatible tools expect this structure
PART 2: MANDATORY MDC METADATA FORMAT
What is MDC Metadata?
Every .mdc file in the .cursor/rules/ directory must have metadata at the top in this format:
---
description: Brief description of what this rule does
globs: file/pattern/to/match/**/*.*
alwaysApply: true/false
---
# Rule content starts here
ABSOLUTE REQUIREMENTS
1. Never Remove or Modify Delimiters
- The
---lines at the beginning and end of metadata are CRITICAL - Removing these breaks the MDC format and disables the rule
- Always preserve exactly three dashes on each line
2. Always Preserve Existing Fields
When updating an MDC file, you MUST preserve:
description: Brief description of the rule's purposeglobs: File patterns that trigger this rulealwaysApply: Whether rule applies to all contexts (true/false)
3. Only Update Content Below Metadata
- Only modify content below the second
---line - Never modify anything between the first and second
---lines - If you need to change metadata fields, do so carefully and preserve the format
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 · 180 lines · 29 tokens per session scan A 2fa7a0f197cd
cursor-rules-management is a cursor rule published in the GitHub repository fbrbovic/cursor-rule-framework (33 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,356 once invoked, about $0.0001 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
cuopt-skill-evolution
Trigger skill evolution — after solving non-trivial problems, propose skill updates.
cursorrules
See CLAUDE.md for full context. Quick rules.
015-context-engineering
Prompt packing, retrieval, and compaction patterns for reliable agent work.
assistant
BASE: routeur d'agents et de process pour votre métier.
moyu
当检测到过度工程模式时自动激活：修改用户未要求的代码、创建不必要的抽象层、 添加未要求的注释/文档/测试、引入不必要的依赖、重写整个文件而非最小编辑、 diff 超出请求范围。用户说"太多了"、"只改 X"、"简单点"时触发。 Activates on over-engineering: modifying unrequested code, unnecessary abstractions, unsolicited comments/docs/tests, unrequested dependencies, full file rewrites, scope-exceeding diffs. Triggers on "too…
cursorrules
This repository contains a structured skill library for AI-assisted product development. Skills are in skills//SKILL.md. Read the relevant SKILL.md before generating any artifact.