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/mervinpraison/praisonai/cursorrulesgit clone --depth 1 https://github.com/MervinPraison/PraisonAIWhat 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 | $0.00153 | $0.00153 |
| Opus 5 | $0.00077 | $0.00077 |
| Sonnet 5 | $0.00031 | $0.00031 |
| Haiku 4.5 | $0.00015 | $0.00015 |
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 3d 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
- Make minimal code changes as possible
- if you are creating function, make sure to name it in more easy, user friendly , optimised manner.
- Never copy the exact code if presented with a code from other location or file or codebase, just make it optimised
- Always Follow the principle LESS IS MORE
- Make it minimal change as possible
- Firstly try not to make any modification to the existing code as possible
- Only modify the existing code if its highly required, without that if it cant be done, then add new code section.
- If you are adding new code, make sure to add it in a way that it can be easily integrated with the existing codebase.
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.
- 3d ago First seen · 8 lines · 153 tokens per session scan A 5f071e81832a
cursorrules is a cursor rule published in the GitHub repository MervinPraison/PraisonAI (9,001 stars, last pushed 2d ago), licensed MIT. It adds 153 tokens to every session, about $0.0008 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
path-traversal-prevention
Path traversal attacks occur when user-controlled input is used to construct file paths, allowing attackers to access files outside the intended directory. This can lead to unauthorized file access, data leakage, or system compromise.
secure-dev-c-sharp
These rules apply to all C#/.NET code in the repository and aim to prevent common security risks through disciplined use of input validation and deserialization, output encoding, and safe APIs.
secure-dev-java
These rules apply to all Java code in the repository (including Spring, Jakarta EE, and standalone apps) and aim to prevent common security risks through disciplined use of input validation, safe APIs, and secure coding patterns.
secure-sql-usage
These rules apply to all code that interacts with SQL databases, regardless of language or framework, including generated code.
secure-dev-ruby
These rules apply to all Ruby code in the repository (including Rails apps, scripts, and gems) and aim to prevent common security vulnerabilities through safe coding patterns, input validation, and proper use of the Ruby standard library.
xxe-prevention
These rules apply to all code that parses or processes XML, regardless of language or framework, including AI-generated code.