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/binding-rules-quick-reference)<a href="https://agentmods.dev/rules/alphabitcore/nexus-gateway/binding-rules-quick-reference"><img src="https://agentmods.dev/badge/rules/alphabitcore/nexus-gateway/binding-rules-quick-reference/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/binding-rules-quick-reference"><img src="https://agentmods.dev/badge/rules/alphabitcore/nexus-gateway/binding-rules-quick-reference.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 | $0.01869 | $0.01869 |
| Opus 5.5 | $0.00748 | $0.00748 |
| Sonnet 5.5 | $0.00374 | $0.00374 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
binding-rules-quick-reference 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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Binding rules — quick reference
Canonical text lives in CLAUDE.md + the rule files listed below. This file is the index so the rules surface in the IDE without re-reading CLAUDE.md every time. When this index disagrees with CLAUDE.md, CLAUDE.md wins.
Top priority — read before any code change
- Pre-edit reading (3 docs) →
pre-edit-reading.mdc. Architecture doc + feature doc + conventions. - Architecture doc triggers (per-module) →
architecture-doc-triggers.mdc(delegates todocs/developers/architecture/README.md). - Mandatory workflow →
sdd-workflow.mdc. Plan + Todo + SDD pipeline.
Always-on rules (every change)
- English only in repo files. Conversation may match user; files stay English.
- Plan + Todo list before edits — required even for one-line fixes.
- Capture every user message as todos — new requests don't interrupt, they queue.
- Complex tasks: Plan + Todo non-waivable →
complex-task-plan-todo.mdc. - Goal-anchored execution — one-line "Goal:" at top of plan; re-state on mid-stream constraint arrival.
- Self-audit before "done" — 4 questions × 2 rounds →
completion-time-self-audit.mdc. - Adversarial product review + less-is-more →
adversarial-product-review.mdc. Steel-man and attack before building; delete instead of add. - Real implementation only in production code. Mocks only in tests.
- Release compat policy (1.0 GA) →
release-compat-policy.mdc. Shipped contracts stay backward compatible (or migrate); internal-only code is greenfield — delete obsolete code, no@deprecated. - No silent skips / no silent forks — ask the user with concrete options when ambiguous.
- Worktree per session →
worktree-per-session.mdc. Each parallel session runs in its owngit worktreeunder./worktrees/. - Sub-agent dispatch discipline →
sub-agent-dispatch.mdc. Goal+non-goals in first 3 lines; 2-round self-audit demanded; per-file touched-paths report required. - Handoff at context-full →
session-handoff.mdc. Offer a handoff doc when auto-compact threshold near / multi-phase closeout / >~50 turns. - Commit reminder — ask before commit; never auto-commit.
- Unit test coverage ≥95% per Go package →
unit-test-coverage-95.mdc. Enforced byscripts/check-go-coverage.sh(pre-commit on staged Go files +npm run check:coverage+ CI). Allowlist additions require user approval + category (cmd / test-helper / DB-bound / OS-bound / network-infra-bound / integration-only).
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.
- 1mo ago First seen · 74 lines · 1,869 tokens per session scan A 921e36348a17
binding-rules-quick-reference is a cursor rule published in the GitHub repository AlphaBitCore/nexus-gateway (25 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,869 tokens to every session, about $0.0075 per session on Opus 5.5. 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.