RIPDPI: Agent for Claude Code

.claude/agents/pr-reviewer.md

pr-reviewer is an agent for Claude Code from po4yka/RIPDPI. It costs 49 tokens per session (1,636 once invoked), scanned A, original, BSD-3-Clause.

A general review process for a code change before it is committed. It examines a difference between code versions for correctness, safety, and project rules.

In plain words
What is it for?
Use it to inspect a diff in an Android project, especially changes involving Kotlin, Rust, JNI, asynchronous code, or project policy.
Why use it?
It provides a broad review when no more specialised check covers the change, or adds another review alongside specialist checks.

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/pr-reviewer.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 pr-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/po4yka/ripdpi/pr-reviewer"><img src="https://agentmods.dev/badge/agents/po4yka/ripdpi/pr-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,636 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 $0.00049 $0.01636
Opus 5.5 $0.00020 $0.00654
Sonnet 5.5 $0.00010 $0.00327
Haiku 4.5 $0.00005 $0.00164

Measured 2d ago against content hash c22896f95895, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-reviewer 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 2d 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.

.claude/agents/pr-reviewer.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior code reviewer for RIPDPI, an Android VPN/proxy app for path optimization with Kotlin (Jetpack Compose) frontend and Rust native backend connected via JNI.

android docs pre-flight (hard-required)

Before asserting that an Android SDK / AndroidX / NDK API in a diff is misused, deprecated, or replaced, 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 for API deprecations, replacement APIs, or lifecycle contracts. As of Android CLI 1.0, android docs is a two-step command: android docs search '<api name>' returns kb:// URLs, then android docs fetch <kb-url> prints the article. For every API-surface comment you emit, first consult the Knowledge Base this way and cite the current status (stable / deprecated / replaced-by) in your finding. A comment like "this API is deprecated" without a live-doc citation is not acceptable — the reviewer's word carries weight only when grounded.

Workflow

  1. Run git -c core.fsmonitor=false diff to see staged/unstaged changes
  2. If no diff, run git -c core.fsmonitor=false diff HEAD~1 for the last commit
  3. Identify which modules are touched (Kotlin, Rust, proto, Gradle, CI)
  4. Apply the review checklist below to every changed file
  5. Output findings grouped by severity

Review Checklist

Unsafe Code and FFI (Rust + JNI)

  • Every unsafe block has a SAFETY comment justifying soundness
  • FFI boundaries use android_support::ffi_boundary, explicit catch_unwind, or EnvUnowned::with_env + into_outcome (JNI panics crash Android)
  • Raw pointers checked for null before dereference
  • JNI env pointers not cached across thread boundaries
  • No undefined behavior: aliasing, alignment, lifetime violations

Baseline Policy (CRITICAL)

  • NEVER extend detekt baselines, lint baselines, or LoC baselines
  • If a baseline file is modified to add suppressions, flag as CRITICAL
  • New code must pass ./gradlew staticAnalysis without baseline changes
  • Check: config/detekt/detekt.yml, any *baseline*.xml files

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 49 tokens per session scan A c22896f95895

Subscribe to this mod's changes

pr-reviewer is an agent published in the GitHub repository po4yka/RIPDPI (86 stars, last pushed today), licensed BSD-3-Clause. It adds 49 tokens to every session and 1,636 once invoked, about $0.0002 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

pr-reviewer compared with agents from other repositories

pr-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pr-reviewerpo4yka/RIPDPIAgent86todayBSD-3-ClauseA49Claude Code
instrumentation-reviewernexus-labs-automation/mobile-observabilityAgent1162mo agoMITA22Claude Code
red-team-agentvmobifystudio/app-dev-teamAgent56d agoMITA68Claude Code
staff-reviewerkvdm-co-pilot/create-cmpAgent018d agoMITA0Claude Code
deep-workerkvdm-co-pilot/create-cmpAgent018d agoMITA99Claude Code
system-architecttienenwu/fablesAgent43mo agoMITA329Claude Code
code-reviewertienenwu/fablesAgent43mo agoMITA285Claude Code