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/ai-gateway-smoke-mandatory)<a href="https://agentmods.dev/rules/alphabitcore/nexus-gateway/ai-gateway-smoke-mandatory"><img src="https://agentmods.dev/badge/rules/alphabitcore/nexus-gateway/ai-gateway-smoke-mandatory/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/ai-gateway-smoke-mandatory"><img src="https://agentmods.dev/badge/rules/alphabitcore/nexus-gateway/ai-gateway-smoke-mandatory.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 | $0.00000 | $0.01100 |
| Opus 5 | $0.00000 | $0.00550 |
| Sonnet 5 | $0.00000 | $0.00220 |
| Haiku 4.5 | $0.00000 | $0.00110 |
Grade A, and why
ai-gateway-smoke-mandatory 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 11d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Gateway / traffic_event smoke (binding)
You are editing AI-Gateway-adjacent code or the traffic_event schema. You MUST run the ai-gateway smoke before reporting the work as done. Unit tests cannot catch the failure modes this smoke is built for: cross-ingress asymmetry (one ingress passes, another silently drops a field), cost / token miscalculation on traffic_event, cache classification bugs, and codec parity regressions between native passthrough and the canonical bridge.
The rule
Any edit that touches:
packages/ai-gateway/**(ingress handlers, providers/specs//, cache, cost, routing, hooks),- the
TrafficEvent/TrafficEventNormalizedtables or anytraffic_event_*migration intools/db-migrate/, packages/shared/transport/normalize/**(canonical normalizer + extractors),packages/ai-gateway/internal/execution/canonicalbridge/(canonical chat-completions bridge) /packages/ai-gateway/internal/providers/canonicalext/(provider-ext fields),packages/shared/traffic/**(adapters, normalize pipeline, dedup, store),- or any provider adapter under
packages/ai-gateway/internal/providers/specs/<name>/,
MUST run an ai-gateway smoke before the completion-time self-audit (Q3) can be answered "yes".
Scope of the smoke run
Pick one based on the blast radius — and call out which you ran in the completion message:
| Scope | Command | When |
|---|---|---|
| Full surface | python3 tests/scripts/smoke-gateway.py --all-ingress |
29 catalog models × 4 ingresses (chat / responses / messages / gemini). Use for shared-code, schema, cost, normalize, canonical-bridge, multi-adapter edits. |
| Partial models | --models <a,b,c> --all-ingress |
Edits provably scoped to ≤3 model families. Pick one model per affected provider. |
| Single ingress | --ingress chat (or responses/messages/gemini) |
Edits to one ingress's codec only. Document why the other three are unaffected. |
| Single model + skip cache | --models X --no-cache |
Targeted regression rerun while iterating on a stream-parser bug. NOT acceptable as the final smoke before "done". |
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.
- 11d ago First seen · 63 lines · 0 tokens per session scan A 6030d29fc25e
ai-gateway-smoke-mandatory is a cursor rule published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,100 tokens. 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
supreme-ai-engineering
Principal AI engineering discipline for production AI/ML/LLM/MLOps/LLMOps systems with eval-first design, pipeline contracts, governance, reliability, QA rigor, operational excellence. On-demand in Cursor.
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.