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/architecture-doc-triggers)<a href="https://agentmods.dev/rules/alphabitcore/nexus-gateway/architecture-doc-triggers"><img src="https://agentmods.dev/badge/rules/alphabitcore/nexus-gateway/architecture-doc-triggers.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 | $0.00403 | $0.00403 |
| Opus 5 | $0.00201 | $0.00201 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
architecture-doc-triggers 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.
What it actually says
Architecture doc triggers — binding
Before editing code in any of the areas listed in docs/developers/architecture/README.md, you MUST first read the listed architecture doc(s).
This rule is one of the three required reads before any code change (see pre-edit-reading.mdc for the full requirement: architecture + feature + conventions). It operationalises Step 1 of the Mandatory Development Workflow in CLAUDE.md ("Architecture") with per-module precision.
How to apply
When the user asks you to edit code, before writing any change:
- Open
docs/developers/architecture/README.md. - Find the row whose "Editing area / file glob" matches.
- Open and read the listed doc(s).
- If your edit area is not covered by any row, that itself is a signal — either the architecture is undocumented (raise it with the user before continuing) or this is a new subsystem that needs its own doc + row.
What to do if you're refactoring
If your PR introduces a new architectural subsystem:
- Write the new
docs/developers/architecture/<service>/<name>-architecture.mdfirst (or in the same PR, ordered before code). - Append the new row to
docs/developers/architecture/README.mdin the same PR. - CI lockstep (
npm run check:arch-doc-triggers) will fail if either side is missing.
What this rule is NOT
- It is not a substitute for the Plan / Todo discipline in CLAUDE.md.
- It is not asking you to read every doc — just the ones for the area you are touching.
- It does not require updating the doc unless the architecture itself is changing.
Skipping this rule requires explicit user approval in chat.
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 · 36 lines · 403 tokens per session scan A 71b53d84b557
architecture-doc-triggers is a cursor rule published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed 6d ago), licensed Apache-2.0. It adds 403 tokens to every session, about $0.0020 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.