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/arxdsilva/vaultWrote 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/arxdsilva/vault/architecture)<a href="https://agentmods.dev/rules/arxdsilva/vault/architecture"><img src="https://agentmods.dev/badge/rules/arxdsilva/vault/architecture/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/arxdsilva/vault/architecture"><img src="https://agentmods.dev/badge/rules/arxdsilva/vault/architecture.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 | $0.00020 | $0.00563 |
| Opus 5.5 | $0.00008 | $0.00225 |
| Sonnet 5.5 | $0.00004 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
architecture 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture
Vault targets multiple operating systems (macOS + Windows, at minimum) with a single shared UI.
Stack: Wails v3 (Go backend + native webview) + React/TypeScript/Tailwind frontend. Full design
spec: docs/SPEC.md.
main.go ← Wails app entry: window, theming, service registration
internal/core/ ← platform-neutral: dir listing, metadata, search/frecency index,
file ops (copy/move/rename), trash interface — no OS-specific APIs
▲
│ a narrow, platform-neutral interface (paths, entries, watch events, operations)
│
internal/platform/darwin/ ← macOS adapter: Trash, FSEvents watcher, path/permission quirks
internal/platform/windows/ ← Windows adapter: Recycle Bin, ReadDirectoryChangesW watcher, path quirks
internal/service/ ← thin Wails-bound service structs exposed to the frontend; call only
into internal/core, never straight into a platform adapter
frontend/ ← React + TypeScript + Tailwind UI; talks only to internal/service
via generated Wails bindings
Rules
| Do | Don't |
|---|---|
| Keep file-system logic (list, search, sort, copy/move/delete) behind a small interface | Scatter OS-specific calls (FSEvents, ReadDirectoryChangesW, etc.) through the UI layer |
| Put OS-specific behavior (trash vs. recycle bin, path separators, case sensitivity, hidden-file conventions) in one adapter per OS | Special-case the OS inline across unrelated files with if runtime.GOOS == ...-style checks |
| Route destructive operations (delete, overwrite, move across volumes) through one reviewable code path | Duplicate delete/move logic per call site |
| Design the core interface so a new platform adapter can be added without touching the UI | Leak a platform adapter's types into shared UI code |
Adding a feature (checklist)
- Failing unit test (TDD) — see
unit-tests-tdd.mdc. - Core — implement in the platform-neutral core; no OS-specific APIs here.
- Adapter — if the feature needs OS-specific behavior, add/extend the adapter for that OS only.
- UI — wire the UI to the core interface, not to the adapter directly.
- Other platforms — confirm the feature degrades sensibly (or is stubbed clearly) on OSes without an adapter yet.
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 · 44 lines · 20 tokens per session scan A bd6c6d655023
architecture is a cursor rule published in the GitHub repository arxdsilva/vault (3 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 563 once invoked, about $0.0001 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 2026-08-31.
Other cursor rules, from other repositories
gonavi-go
A Go coding rule set for the GoNavi repository, based on common Go style guides and the project's own conventions. It covers file structure, errors, context, concurrency, logging, and tests.
backend
You are an expert in Go, Gin, Gorm, Gen, Cosy (https://cosy.uozi.org/) with a deep understanding of best practices and performance optimization techniques in these technologies.
miro-best-practices
MCP server for controlling Miro whiteboards with AI assistants.
go-project-structure
This rule ensures that Go projects follow a consistent and idiomatic structure, making the codebase easier to navigate, maintain, and scale.
best-practices
Go Best Practices - enforces current best practices when working with Go code.
go-testing-practices
Go Testing Best Practices.