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.
npx agentmods add rules/hyperb1iss/droidmind/002_cursor_rulesgit clone --depth 1 https://github.com/hyperb1iss/droidmindWhat 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 | $0.00000 | $0.00240 |
| Opus 5 | $0.00000 | $0.00120 |
| Sonnet 5 | $0.00000 | $0.00048 |
| Haiku 4.5 | $0.00000 | $0.00024 |
Grade A, and why
002_cursor_rules 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 yesterday.
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
.mdc File Structure & Best Practices:
File Naming: NNN_name.mdc (NNN = 001-299)
- 001-099: Core/workspace rules
- 100-199: Integration rules
- 200-299: Pattern rules Higher numbers take precedence if rules conflict
UI Components:
-
Description (top)
- Brief purpose summary
- Appears in AI context
-
Globs (top)
- Comma-separated list
- Example: /dir1//*,/dir2//,/dir3/**/
- Use standard glob syntax
-
Body Text (this section)
- Keep under 50 lines
- Use concise/shorthand
- Tag files with @
- Focus on key directives
Best Practice: The assistant may propose changes to .mdc files for the user to copy into the UI. The assistant should not attempt direct file edits to .mdc files.
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.
- yesterday First seen · 31 lines · 0 tokens per session scan A a8f51bdb51bf
002_cursor_rules is a cursor rule published in the GitHub repository hyperb1iss/droidmind (430 stars, last pushed 7mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 240 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
compose-coroutines
Compose scroll/coroutine patterns — prevent programmatic scroll from being mistaken for user scroll, cancellation-safe flag resets.
android-viewmodel
Android ViewModel conventions — StateFlow, repository abstraction, coroutines, no LiveData.
shared-module
KMP shared module constraints — no platform imports in domain/, expect/actual conventions, pure Kotlin business logic.
swiftui-accessibility
SwiftUI accessibility rules for VoiceOver — labels, hints, traits, values, and attribute preservation.
utilities
Lodash 和 Moment.js 工具庫使用規範.
android-gradle-build-logic
Shape Android build logic with Gradle, version catalogs, plugins, convention patterns, and toolchain compatibility.