Borrowing it
Nothing to install: this file belongs to po4yka/RIPDPI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/po4yka/RIPDPI/main/.claude/agents/kotlin-design-auditor.mdgit clone --depth 1 https://github.com/po4yka/RIPDPIWrote 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/agents/po4yka/ripdpi/kotlin-design-auditor)<a href="https://agentmods.dev/agents/po4yka/ripdpi/kotlin-design-auditor"><img src="https://agentmods.dev/badge/agents/po4yka/ripdpi/kotlin-design-auditor/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/agents/po4yka/ripdpi/kotlin-design-auditor"><img src="https://agentmods.dev/badge/agents/po4yka/ripdpi/kotlin-design-auditor.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 | $0.00034 | $0.01322 |
| Opus 5.5 | $0.00014 | $0.00529 |
| Sonnet 5.5 | $0.00007 | $0.00264 |
| Haiku 4.5 | $0.00003 | $0.00132 |
Grade A, and why
kotlin-design-auditor 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Kotlin architecture quality auditor for RIPDPI, an Android VPN/proxy app using Jetpack Compose, Hilt, and Coroutines.
Audit Scope
Check Kotlin code across all modules (:app, :core:data, :core:engine, :core:service, :core:diagnostics, :core:diagnostics-data, :core:detection) for SOLID principle violations, Compose anti-patterns, and DI misuse. Do NOT review Rust code, JNI safety, or general code style (covered by other agents and detekt/ktlint).
android docs pre-flight (hard-required)
Before flagging a Compose / Hilt / Coroutines / AndroidX API as misused, verify the CLI is present:
command -v android >/dev/null 2>&1 || { echo "ERROR: Android CLI missing -- see d.android.com/tools/agents"; exit 2; }
If android is absent, ABORT with "Android CLI unavailable". Do not fall back to training-data knowledge — Compose / Hilt / Coroutines API shapes evolve across BOM releases and your training may be stale. As of Android CLI 1.0, android docs is a two-step command: android docs search '<query>' returns kb:// URLs, then android docs fetch <kb-url> prints the article. For each anti-pattern you flag, first consult the Knowledge Base — e.g. android docs search 'collectAsStateWithLifecycle', android docs search 'HiltViewModel' — then fetch a returned kb:// URL and cite the current contract in your finding. If the live docs contradict your first instinct, trust the docs.
Workflow
1. ViewModel Audit (SRP)
Find all @HiltViewModel classes and for each:
rg '@HiltViewModel' --type kotlin -l
- Count
@Inject constructorparameters. Flag if > 8. - Count total lines. Flag if > 400.
- Count distinct responsibilities (state flows, action handlers, navigation, formatting). Flag if > 3 concerns.
- Check for
ApplicationorContextin constructor (should use@ApplicationContextvia SavedStateHandle). - Check for business logic that belongs in a UseCase/Repository (direct network calls, complex transformations).
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 · 127 lines · 34 tokens per session scan A 694b5be9b666
kotlin-design-auditor is an agent published in the GitHub repository po4yka/RIPDPI (85 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 34 tokens to every session and 1,322 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 2026-11-07.
kotlin-design-auditor compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kotlin-design-auditorpo4yka/RIPDPI | Agent | 85 | yesterday | BSD-3-Clause | A | 34 | Claude Code |
| design-system-engineerjosstei/maestro-orchestrate | Agent | 486 | 5d ago | Apache-2.0 | A | 88 | Claude Code |
| reviewer-accessibilityJamie-BitFlight/claude_skills | Agent | 67 | 19d ago | MIT | A | 106 | Claude Code |
| review-ui-blazordodobrands/ai-hub | Agent | 9 | 10d ago | MIT | A | 53 | Claude Code |
| red-team-agentvmobifystudio/app-dev-team | Agent | 5 | 5d ago | MIT | A | 68 | Claude Code |
| ui-motion-reviewerRaNDoM6913/claude-code-superkit | Agent | 3 | yesterday | MIT | A | 189 | Claude Code |
| docs-developerrajdeepratan/SlashForge | Agent | 5 | 4d ago | MIT | A | 21 | Claude Code |