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/arch-layer-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/arch-layer-auditor)<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.
<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>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 | $0.02131 |
| Opus 5.5 | $0.00014 | $0.00852 |
| Sonnet 5.5 | $0.00007 | $0.00426 |
| Haiku 4.5 | $0.00003 | $0.00213 |
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.
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
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 · 158 lines · 34 tokens per session scan A 14e4d59e5db2
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.
arch-layer-auditor compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| arch-layer-auditorpo4yka/RIPDPI | Agent | 85 | yesterday | BSD-3-Clause | A | 34 | Claude Code |
| kotlin-revieweraffaan-m/ECC | Agent | 299k | yesterday | MIT | A | 38 | Claude Code, Kiro |
| kotlin-abi-reviewHeapy/kortex | Agent | 7 | 5d ago | Apache-2.0 | A | 0 | Claude Code |
| kotlin-code-reviewerpranav8494/team-of-agents | Agent | 7 | 1mo ago | MIT | A | 62 | Claude Code |
| rust-change-revieweradulari/forge | Agent | 12 | 2d ago | AGPL-3.0 | A | 21 | Claude Code |
| kotlin-reviewerloulanyue/awesome-claude-notes | Agent | 271 | 1mo ago | MIT | A | 38 | Claude Code |
| kotlin-reviewerFmarzochi/EGC | Agent | 68 | today | Apache-2.0 | A | 38 | Claude Code |