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/brycegao/android-finance-spec/kotlingit clone --depth 1 https://github.com/brycegao/android-finance-specWrote 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/brycegao/android-finance-spec/kotlin)<a href="https://agentmods.dev/rules/brycegao/android-finance-spec/kotlin"><img src="https://agentmods.dev/badge/rules/brycegao/android-finance-spec/kotlin.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 | $0.00209 | $0.00209 |
| Opus 5 | $0.00105 | $0.00105 |
| Sonnet 5 | $0.00042 | $0.00042 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
kotlin 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 4d 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
Android Finance Spec Rules
When generating, editing, or reviewing this repository, follow:
specs/finance-number-skill.mdspecs/rtl-adaption.mdspecs/kotlin-style.md
Hard rules:
- Treat every MUST and MUST NOT as a hard gate.
- Keep
skills/android-finance-spec/references/synchronized withspecs/. - Reuse existing repository structure, scripts, and naming.
- Do not add unrelated framework, dependency, or prompt assets.
- Run
python3 scripts/sync_skill_refs.pyafter spec edits. - Run
python3 -m unittest tests/test_android_finance_scan.pyafter scanner or example edits.
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.
- 4d ago First seen · 28 lines · 209 tokens per session scan A 02b0dcff1211
kotlin is a cursor rule published in the GitHub repository brycegao/android-finance-spec (4 stars, last pushed 2mo ago), licensed MIT. It adds 209 tokens to every session, about $0.0010 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 2026-08-31.
Other cursor rules, from other repositories
cursorrules
You are a senior Android developer. Follow these rules strictly when writing or modifying Android/Kotlin code.
compose-ui
Jetpack Compose UI rules: state management, recomposition, performance, accessibility, Material 3.
data-layer
Data layer rules: Room, DataStore, networking, offline-first, Paging 3, serialization.
architecture
Android architecture rules: layered architecture, UDF, Repository pattern, ViewModel, UseCases.
modern-android
Modern Android rules: edge-to-edge, predictive back, splash screen, WorkManager, lifecycle, coroutines.
performance
Performance rules: Compose recomposition, lazy layouts, app startup, memory, benchmarking.