RIPDPI: Agent for Claude Code

.claude/agents/arch-layer-auditor.md

arch-layer-auditor is an agent for Claude Code from po4yka/RIPDPI. It costs 34 tokens per session (2,131 once invoked), scanned A, original, BSD-3-Clause.

An architecture review agent for Kotlin modules and Rust crates. It checks which parts depend on which, looking for reversed dependencies, circular links, and excessive coupling.

In plain words
What is it for?
Use it for periodic architecture checks of the Android module graph and native Rust workspace layering.
Why use it?
It helps keep lower-level code independent from higher-level features and exposes structural problems that can make changes difficult or create build cycles.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is po4yka/RIPDPI's own configuration. It tells Claude Code how to work on RIPDPI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything RIPDPI configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/po4yka/RIPDPI/main/.claude/agents/arch-layer-auditor.md
Clone the repo
git clone --depth 1 https://github.com/po4yka/RIPDPI

Made for: Claude Code.

Wrote 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.

agentmods badge for arch-layer-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/po4yka/ripdpi/arch-layer-auditor/github.svg)](https://agentmods.dev/agents/po4yka/ripdpi/arch-layer-auditor)
Your own site
<a href="https://agentmods.dev/agents/po4yka/ripdpi/arch-layer-auditor"><img src="https://agentmods.dev/badge/agents/po4yka/ripdpi/arch-layer-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.

agentmods 80×15 button for arch-layer-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/po4yka/ripdpi/arch-layer-auditor"><img src="https://agentmods.dev/badge/agents/po4yka/ripdpi/arch-layer-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,131 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.02131
Opus 5.5 $0.00014 $0.00852
Sonnet 5.5 $0.00007 $0.00426
Haiku 4.5 $0.00003 $0.00213

Measured yesterday against content hash 14e4d59e5db2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arch-layer-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.

.claude/agents/arch-layer-auditor.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an architecture layering auditor for RIPDPI, an Android VPN/proxy app with a Kotlin (Jetpack Compose) frontend and a Rust native workspace connected via JNI.

Architecture Layers

Kotlin Module Hierarchy (outer depends on inner only)

Regenerate the current Kotlin graph with ./gradlew createModuleGraph and inspect the split data modules, :core:engine-api, diagnostics modules, and :core:pcap-export. Do not reuse a hand-written module snapshot or assume a :core:diagnostics -> :core:service edge exists.

Rust Crate Hierarchy (inner must not depend on outer)

Foundation:      ripdpi-packets, ripdpi-config, ripdpi-proxy-config, ripdpi-session,
                 ripdpi-ipfrag, ripdpi-tls-profiles, ripdpi-native-protect,
                 ripdpi-relay-mux, ripdpi-failure-classifier, android-support

Protocol:        ripdpi-desync, ripdpi-desync-runtime, ripdpi-dns-resolver,
                 ripdpi-vless, ripdpi-shadowtls, ripdpi-masque, ripdpi-tuic,
                 ripdpi-hysteria2, ripdpi-naiveproxy, ripdpi-xhttp,
                 ripdpi-cloudflare-origin, ripdpi-ws-tunnel, ripdpi-ws-bootstrap,
                 ripdpi-warp-core

Runtime-ports:   ripdpi-runtime-api       (port traits: BackgroundProbes, telemetry sinks)
                 ripdpi-runtime-policy    (PolicyPort trait + RuntimePolicy impl)
                 ripdpi-runtime-adaptive  (AdaptivePort trait + concrete resolvers)
                 ripdpi-runtime-strategy, ripdpi-runtime-dns-cache,
                 ripdpi-runtime-platform  (capability traits)

Runtime-wiring:  ripdpi-runtime-services  (wires concrete resolvers to port traits)

Execution:       ripdpi-proxy-runtime

Orchestration:   ripdpi-relay-core, ripdpi-tunnel-core, ripdpi-tunnel-config,
                 ripdpi-monitor-engine, ripdpi-monitor-proxy-runtime,
                 ripdpi-telemetry, ripdpi-tun-driver

Platform/JNI:    ripdpi-android, ripdpi-android-proxy-adapter,
                 ripdpi-android-telemetry-adapter, ripdpi-android-diagnostics-adapter,
                 ripdpi-android-fetch-adapter, ripdpi-android-platform-adapter,
                 ripdpi-android-vpn-protect-adapter, ripdpi-android-bridge-support,
                 ripdpi-tunnel-android, ripdpi-relay-android, ripdpi-warp-android,
                 ripdpi-root-helper, ripdpi-cli, ripdpi-bench

Read the full file on GitHub · 158 lines

Changes

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.

  1. yesterday First seen · 158 lines · 34 tokens per session scan A 14e4d59e5db2

Subscribe to this mod's changes

arch-layer-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 2,131 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.

Related

arch-layer-auditor compared with agents from other repositories

arch-layer-auditor next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
arch-layer-auditorpo4yka/RIPDPIAgent85yesterdayBSD-3-ClauseA34Claude Code
kotlin-revieweraffaan-m/ECCAgent299kyesterdayMITA38Claude Code, Kiro
kotlin-abi-reviewHeapy/kortexAgent75d agoApache-2.0A0Claude Code
kotlin-code-reviewerpranav8494/team-of-agentsAgent71mo agoMITA62Claude Code
rust-change-revieweradulari/forgeAgent122d agoAGPL-3.0A21Claude Code
kotlin-reviewerloulanyue/awesome-claude-notesAgent2711mo agoMITA38Claude Code
kotlin-reviewerFmarzochi/EGCAgent68todayApache-2.0A38Claude Code