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/aiagentwithdhruv/ai-dev-stack/70-securitygit clone --depth 1 https://github.com/aiagentwithdhruv/ai-dev-stackWhat 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 | $0.00236 | $0.00236 |
| Opus 5 | $0.00118 | $0.00118 |
| Sonnet 5 | $0.00047 | $0.00047 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
70-security 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
Security rules:
- Never hardcode secrets, API keys, tokens, credentials, or private URLs.
- Never log passwords, tokens, raw secrets, or sensitive user content.
- Validate and sanitize all user inputs.
- Treat uploads, URLs, prompts, and external content as untrusted.
- Enforce authentication and authorization checks on protected resources.
- Use least-privilege access patterns.
- Add rate limiting to sensitive or expensive endpoints.
- Use secure defaults.
AI-specific security:
- Add prompt injection resistance where relevant.
- Validate tool inputs and outputs.
- Restrict tool access by policy.
- Protect system instructions and internal configuration.
- Handle unsafe model output before returning it to the user.
Infra/security hygiene:
- Prefer environment variables and secret managers.
- Avoid broad wildcard permissions in cloud configs.
- Do not expose internal services publicly unless required.
Do not:
- Assume client-side validation is enough.
- Return internal error details to end users in production.
- Store plaintext passwords or tokens in databases.
- Use default credentials or weak secrets in any environment.
- Disable HTTPS or certificate validation.
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 · 34 lines · 236 tokens per session scan A afa1d6d1280e
70-security is a cursor rule published in the GitHub repository aiagentwithdhruv/ai-dev-stack (10 stars, last pushed 2mo ago), licensed MIT. It adds 236 tokens to every session, about $0.0012 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
cursorrules
You are building an AI/ML project with Python. The project uses PyTorch for model training, handles data pipelines with proper validation, tracks experiments systematically, and follows production ML engineering practices. Code is type-hinted, tested, and reproducible.
cursorrules
Code exhibits taste — Torvalds' term for finding the formulation where special cases disappear. Seek representations where edge cases become impossible, the type system proves correctness, and the API guides users into the pit of success.
angular
Angular: signals, standalone components, RxJS patterns.
django
Django: models, views, ORM best practices.
java
Modern Java: records, sealed classes, streams, virtual threads.
javascript
Modern JavaScript: ES2023+, async patterns, common traps.