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/Project-VIC-International/Agentic-AI-Development-CourseWrote 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/project-vic-international/agentic-ai-development-course/security-compliance)<a href="https://agentmods.dev/rules/project-vic-international/agentic-ai-development-course/security-compliance"><img src="https://agentmods.dev/badge/rules/project-vic-international/agentic-ai-development-course/security-compliance.svg" alt="Measured on agentmods" 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 | $0.03538 | $0.03538 |
| Opus 5 | $0.01769 | $0.01769 |
| Sonnet 5 | $0.00708 | $0.00708 |
| Haiku 4.5 | $0.00354 | $0.00354 |
Grade A, and why
security-compliance 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 8d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Compliance: NIST SP 800-53 Rev. 5 and FBI CJIS Security Policy
This project processes Criminal Justice Information (CJI) and law-enforcement-sensitive evidence — potentially including CSAM in ICAC casework. All code MUST comply with NIST SP 800-53 Rev. 5 and the FBI CJIS Security Policy (currently v5.9.x). Non-compliance is not a bug — it is a deployment blocker, and in many jurisdictions a legal liability for the agency operating the tool.
The constitution's "Security and Privacy" section is the high-level statement. This rule is the enforceable detail the agent applies when writing code.
The full mappings should live in your repo at docs/security/nist-800-53-mapping.md and docs/security/cjis-compliance-mapping.md. Update them every time a new feature touches a control family.
These are the normal security control frameworks used within the United States of America. You may need to adjust this to your country or regional security control frameworks. Many security control frameworks have overlaps but they are not the same. If you want to run your software in many countries you may need to apply various security framework profiles to your application.
Reference Documents
- FBI CJIS Security Policy — https://www.fbi.gov/services/cjis/cjis-security-policy-resource-center
- NIST SP 800-53 Rev. 5 — https://csrc.nist.gov/publications/detail/sp/800-53/rev-5/final
- NIST Cybersecurity Framework — https://www.nist.gov/cyberframework
- NIST CFTT (tool validation) — https://www.nist.gov/itl/ssd/software-quality-group/computer-forensics-tool-testing-program-cftt
Applicable Control Families
When implementing any feature that touches the areas below, map your implementation to the specific controls and document the mapping in the spec's "Security Controls" section (per the speckit-workflow rule).
Access Control (AC)
- AC-2 — Account management: All multi-user mode users have individual accounts; no shared credentials. Agency identity systems map 1:1 to investigators / examiners. Never ship a default
admin/adminaccount. - AC-3 — Access enforcement: Implement Role-Based Access Control (RBAC). Every API endpoint and MCP tool that mutates state MUST check the user's permission, not just their authentication.
- AC-6 — Least privilege: Each component runs with the minimum permissions it needs. Plugin sandboxing for any third-party / dynamically-loaded code MUST drop privileges before executing untrusted code. Container deployments run as non-root.
- AC-7 — Unsuccessful login attempts: Lock accounts after a configurable threshold of failed authentications. CJIS requires a maximum of 5 consecutive failures. Lockout state is persisted and auditable.
- AC-8 — System use notification: GUI and API surfaces MUST display a configurable legal banner before login. The banner text is set per deployment by the operating agency.
- AC-11 — Session lock: Auto-lock after 30 minutes of inactivity (CJIS). API / MCP sessions enforce token expiry.
- AC-17 — Remote access: All remote connections (REST API, MCP over network transports, multi-user database connections) MUST use TLS 1.2 or higher.
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.
- 8d ago First seen · 182 lines · 3,538 tokens per session scan A 9e1e0e31c66f
security-compliance is a cursor rule published in the GitHub repository Project-VIC-International/Agentic-AI-Development-Course (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 3,538 tokens to every session, about $0.0177 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.