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/four-surface-review)<a href="https://agentmods.dev/rules/project-vic-international/agentic-ai-development-course/four-surface-review"><img src="https://agentmods.dev/badge/rules/project-vic-international/agentic-ai-development-course/four-surface-review/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/project-vic-international/agentic-ai-development-course/four-surface-review"><img src="https://agentmods.dev/badge/rules/project-vic-international/agentic-ai-development-course/four-surface-review.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 | $0.01357 | $0.01357 |
| Opus 5 | $0.00678 | $0.00678 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
four-surface-review 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 9d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Four-Surface Impact Review
A modern CAC mission tool exposes its functionality through four surfaces. Every change — feature, fix, refactor, or optimization — MUST be reviewed for its impact on all four. This is not optional. A change that improves one surface while leaving another broken or inconsistent is incomplete.
This rule encodes one of the core lessons of this course: humans and AI agents both consume your tool, but they do so through different doors. If you only build the front door, half your users (and most of your AI agents) cannot get in.
The Four Surfaces
| Surface | What It Is | Primary Users |
|---|---|---|
| GUI (Graphical User Interface) | Buttons, menus, panels, the visual application | Investigators and examiners working interactively, often under time pressure |
| CLI (Command-Line Interface) | Terminal commands, scripts, batch processing | Examiners running unattended triage; lab automation; CI pipelines |
| API (Application Programming Interface) | HTTP/REST endpoints, library functions | Lab management systems; integrations with other forensic tools; multi-user deployments |
| MCP (Model Context Protocol) | Tools, resources, and prompts an AI agent can invoke | AI assistants helping investigators; automated triage; LLM-driven analysis workflows |
If your project does not yet expose all four surfaces, the spec MUST say so explicitly and the missing surfaces MUST appear on the project roadmap. Do not silently treat the GUI as the only surface.
The Review Checklist
Before considering any change complete, answer these questions for each surface:
GUI
- Does this change need to be visible or accessible in the GUI?
- If a new capability was added, is there a corresponding view, panel, menu item, or toolbar action?
- Does the GUI use investigator-familiar terminology (per the CAC ontology and the project constitution's investigator-first language principle)?
- Is the interaction designed for an investigator under stress and time pressure, not for a software engineer?
- Does the GUI surface evidence provenance — can the user trace how a result was produced (which model, which version, which inputs, which timestamp)?
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.
- 9d ago First seen · 85 lines · 1,357 tokens per session scan A fed4fa602ff3
four-surface-review 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 1,357 tokens to every session, about $0.0068 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
clean-code-reviewer
Eliminates technical debt using SOLID, DRY, YAGNI, and Addy Osmani production-grade engineering principles. / TR: SOLID, DRY, YAGNI ve Addy Osmani üretim seviyesi mühendislik ilkeleri ile kod kalitesini denetleyen yetenek.
sweep-benchmarks
Audit xrspatial modules for asv benchmark coverage gaps: missing benchmarks, backend parameterization gaps, unrepresentative inputs, broken or silently-skipped benchmarks.
code-review
BMAD BMM Agent: code-review.
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.