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/AlphaBitCore/nexus-gatewayWrote 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/alphabitcore/nexus-gateway/adversarial-product-review)<a href="https://agentmods.dev/rules/alphabitcore/nexus-gateway/adversarial-product-review"><img src="https://agentmods.dev/badge/rules/alphabitcore/nexus-gateway/adversarial-product-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/alphabitcore/nexus-gateway/adversarial-product-review"><img src="https://agentmods.dev/badge/rules/alphabitcore/nexus-gateway/adversarial-product-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 | $0.00523 | $0.00523 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
adversarial-product-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 10d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial product review + less-is-more (binding)
Two halves of the same product discipline. Apply both to any proposed feature, config knob, UI surface, menu item, behavior change, or "wouldn't it be nice if…" idea — including user proposals.
Half 1 — Steel-man, then attack
Before implementing, surface in chat:
- (a) Is the user-facing value clear and large?
- (b) How often will real users hit this path?
- (c) Could a sensible default, an existing surface, or a convention solve it without a new knob?
- (d) Is the placement correct (right table / page / layer / menu) or is it being attached to the nearest convenient form?
- (e) Does the cost (UI surface, config burden, cognitive load, future maintenance) exceed the value?
Counter-arguments go in chat BEFORE implementation. If they're strong and unanswered, push back with "I'd challenge: …" rather than building. If the user persists after seeing them, that's signal — proceed.
Half 2 — Less is more / delete instead of add
Defaults must work out of the box — admins should not face a 5-tab detail page or a JSON editor for every protocol quirk. Spring-style: sensible default for every knob; configuration only when divergence is genuinely needed.
When in doubt about adding a UI surface, config field, menu item, or code path: delete instead.
Prefer:
- Adapter / runtime auto-fills over admin-facing config. Canonical pattern: Anthropic
max_tokensdefault inpackages/ai-gateway/internal/providers/specs/anthropic/codec/codec.go— adapter fills the protocol-required field from model capability when caller omits it. - Global settings over per-route / per-rule overrides unless real divergence is documented.
- One location per concept over scattering across menus.
- Extending an existing surface over adding a new tab / page / route.
New surfaces require an explicit "what user journey, how often, why nothing existing covers it" in the plan; without that, the default is no.
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.
- 10d ago First seen · 42 lines · 523 tokens per session scan A 20d6644e0759
adversarial-product-review is a cursor rule published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed 8d ago), licensed Apache-2.0. It adds 523 tokens to every session, about $0.0026 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
solana-security
Solana Security Standard (SOL-0XX) - flag and fix Solana/Anchor security bugs.
recipe_author
How to author a recipe in ks-cookbook.
20-phi-redaction-first
PHI redaction first — Presidio gate, token handling, and minimum necessary LLM access for HIPAA workflows.
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.