Borrowing it
Nothing to install: this file belongs to Funky-Rhyme/Vpnconf. 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/Funky-Rhyme/Vpnconf/main/CLAUDE.mdgit clone --depth 1 https://github.com/Funky-Rhyme/VpnconfWrote 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/instructions/funky-rhyme/vpnconf/claude-md)<a href="https://agentmods.dev/instructions/funky-rhyme/vpnconf/claude-md"><img src="https://agentmods.dev/badge/instructions/funky-rhyme/vpnconf/claude-md/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/instructions/funky-rhyme/vpnconf/claude-md"><img src="https://agentmods.dev/badge/instructions/funky-rhyme/vpnconf/claude-md.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 | $0.01072 | $0.01072 |
| Opus 5 | $0.00536 | $0.00536 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
Vpnconf CLAUDE.md 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — agent onboarding
vpnconf — cross-platform C# / .NET 10 CLI that lets a personal VPN coexist with a corporate one.
It reads routes the corporate VPN added, finds overlaps with a personal split-tunnel CIDR list, and
"punches holes": subtracts the corporate subnets from the personal CIDRs and re-covers the remainder
with a minimal CIDR set. Scope is IPv4 only.
Read this first, then README.md (usage), .cursor/docs/vpn-route-conflict-cli-spec.md (full spec +
"Реализовано" + "Extending"), and .cursor/rules/project-standards.mdc (quality bar).
Hard invariants — do not violate
- Never modify
.cursor/11.02.2026_proxy-list.json. It is reference test data (2667 CIDRs). - Never overwrite a file without
--backup. File writes for the ip-list go throughCli/SafeFile.Write, which refuses to clobber an existing file unless a backup is made. Keep this. Enginestays pure and deterministic — no I/O, no OS calls, same input ⇒ same output. OS- and filesystem-specific code lives behind adapters inInfrastructure/Cli.- Keep it AOT-safe.
PublishAot=true. Use System.Text.Json source generation (seeParsing/IpListJson.cs,Output/PatchPlanJson.cs), not reflection-based (de)serialization. NoJsonSerializer.Serialize(object, Type, options)overloads — they warn under AOT. - IPv4 only right now. IPv6 is out of scope unless explicitly asked.
Build / test / run
dotnet build # whole solution
dotnet test # xUnit engine/parser tests (currently 32)
dotnet run --project NetworkRoutesConflictResolver -- <command> [options]
./publish-aot.ps1 # native AOT binary (needs VS C++ workload)
The output binary is named vpnconf (via <AssemblyName> in the csproj), not the project name.
The interactive menu (vpnconf with no args, or vpnconf menu) needs a real terminal (TTY).
Module map (modular monolith)
| Project folder | Responsibility | Key types |
|---|---|---|
Model |
Immutable data contracts | Ipv4Cidr + Ipv4Ranges (the CIDR workhorse), RouteEntry, CidrEntry, PatchPlan, RouteConflict |
Engine |
Pure algorithms | ConflictDetector, CidrSubtractEngine, CidrMinimizer, PatchPlanner, PatchApplier |
Parsing |
Input normalization | IIpListParser/IpListParserRegistry (+ Json/PlainText impls), RouteTableParser (text dumps) |
Infrastructure/Routes |
OS adapters | IRouteTableProvider → WindowsRouteTableProvider (P/Invoke GetIpForwardTable); RouteTableProviderFactory |
Output |
Reports + serialization | ReportWriter (Spectre.Console), IpListSerializer, PatchPlanSerializer |
Cli |
Args + commands | CliApplication, Commands/* (Interactive,Resolve,Analyze,Plan,Apply), ArgMap, SafeFile, RoutePrompts |
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.
- 10d ago First seen · 66 lines · 1,072 tokens per session scan A 9cfa343b54af
Vpnconf CLAUDE.md is an instructions file published in the GitHub repository Funky-Rhyme/Vpnconf (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,072 tokens to every session, about $0.0054 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.