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/gurbaaz27/cursorrulesWrote 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/gurbaaz27/cursorrules/auto-update-readme)<a href="https://agentmods.dev/rules/gurbaaz27/cursorrules/auto-update-readme"><img src="https://agentmods.dev/badge/rules/gurbaaz27/cursorrules/auto-update-readme/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/gurbaaz27/cursorrules/auto-update-readme"><img src="https://agentmods.dev/badge/rules/gurbaaz27/cursorrules/auto-update-readme.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 | $0.00000 | $0.00369 |
| Opus 5.5 | $0.00000 | $0.00148 |
| Sonnet 5.5 | $0.00000 | $0.00074 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
auto-update-readme 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.
What it actually says
Auto-Update README.md
When a rule file in the rules/ directory is created, edited, or deleted, you MUST update README.md to reflect the changes.
Update Process
1. Scan Rules Directory
For each .mdc file in rules/:
- Extract the rule name from filename (without extension)
- Read the
descriptionfield from the frontmatter - Skip
.mini.mdcfiles in the main table (list them as sub-items or variants)
2. Update the Rules Table
Update the ## Rules section in README.md with the current rules:
## Rules
| Rule | Description |
| ---- | ----------- |
| [rule-name](rules/rule-name.mdc) | Description from frontmatter |
3. Grouping
If a rule has a .mini.mdc variant:
- List the main rule in the table
- Add the mini version as a secondary link or note
Example:
| [auto-update-llms-robots-txt](rules/auto-update-llms-robots-txt.mdc) | Auto-update llms.txt and robots.txt ([mini](rules/auto-update-llms-robots-txt.mini.mdc)) |
4. Preserve Structure
- Keep the existing README structure intact
- Only modify the Rules table section
- Preserve any custom content above/below the table
Output
After updating, briefly confirm:
✅ Updated README.md
- Added: new-rule
- Rules count: X
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 · 58 lines · 0 tokens per session scan A 50a62f53b94c
auto-update-readme is a cursor rule published in the GitHub repository gurbaaz27/cursorrules (1 stars, last pushed 10mo ago), licensed CC0-1.0. It costs nothing until one of its globs matches a file; then it loads 369 tokens. 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
refactoring
Refactoring: systematic approach, extract/inline, guard clauses, early returns.
cross-tool-config
Cross-tool AI config: what transfers between Cursor, Claude Code, Copilot, Windsurf, Gemini, and Codex.
angular
Angular: signals, standalone components, RxJS patterns.
django
Django: models, views, ORM best practices.
fastapi
FastAPI: Pydantic v2, dependency injection, async.
tailwind-css
Tailwind CSS: utility patterns, design tokens, component extraction.