verify-networking-plugin CLAUDE.md

verify-networking-plugin CLAUDE.md is an instructions file for coding agents from Laotree/verify-networking-plugin. It costs 1,659 tokens per session, scanned A, original, MIT.

Repository instructions for verify-networking, a Rust program that checks network access before starting coding agents such as Claude or Codex. It can also run as a local proxy service.

In plain words
What is it for?
They help build and lint the Rust program, run it directly or as a daemon, choose a port, install its shell wrapper, and run tests.
Why use it?
They provide the commands and architecture needed to build, check, install, and test the network guard. This helps ensure agent launches are inspected consistently.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/laotree/verify-networking-plugin/claude-md
Clone the repo
git clone --depth 1 https://github.com/Laotree/verify-networking-plugin

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 verify-networking-plugin CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/laotree/verify-networking-plugin/claude-md.svg)](https://agentmods.dev/instructions/laotree/verify-networking-plugin/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/laotree/verify-networking-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/laotree/verify-networking-plugin/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,659 This file is loaded in full into every session.
When invoked 1,659 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01659 $0.01659
Opus 5 $0.00830 $0.00830
Sonnet 5 $0.00332 $0.00332
Haiku 4.5 $0.00166 $0.00166

Measured 4d ago against content hash 365c9c1e33c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-networking-plugin 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 4d 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.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

cargo build --release          # build the binary
cargo clippy                   # lint
./install.sh                   # build + install binary + add shell wrapper to RC file

To test the binary directly:

./target/release/verify-networking; echo "exit: $?"

# Test daemon mode (starts proxy, Ctrl+C to stop)
./target/release/verify-networking --daemon

# Test daemon mode with custom port
./target/release/verify-networking --daemon --port 9999

Makefile targets

make          # debug build
make release  # release build
make test     # run tests
make lint     # clippy
make fmt      # format source
make clean    # remove build artifacts
make install  # build + install + patch shell RC
make hooks    # install git pre-push hook

Architecture

The plugin is a Rust binary installed at ~/.claude/plugins/verify-networking. install.sh adds shell wrapper functions to the user's RC file that intercept every claude (and codex, if installed) invocation before the process starts:

claude() {
    local checker="$HOME/.claude/plugins/verify-networking"
    [[ -x "$checker" ]] && { "$checker" claude || return 1; }
    command claude "$@"
}

codex() {
    local checker="$HOME/.claude/plugins/verify-networking"
    [[ -x "$checker" ]] && { "$checker" codex || return 1; }
    command codex "$@"
}

The tool name (claude / codex) is passed as the first argument so the binary knows which API endpoint to probe. This ensures the network check runs before either tool makes any outbound requests.

Checks (src/checks.rs): All three run concurrently via tokio::join!. Targets differ by tool:

Check Claude target Codex target
DNS api.anthropic.com api.openai.com
Exit IP ipinfo.io/json — blocks CN/HK/KP/CU/IR/SY/RU/BY same
Connectivity 3 × TCP to api.anthropic.com:443, 5 s timeout 3 × TCP to api.openai.com:443, 5 s timeout

Read the full file on GitHub · 159 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. 4d ago First seen · 159 lines · 1,659 tokens per session scan A 365c9c1e33c7

Subscribe to this mod's changes

verify-networking-plugin CLAUDE.md is an instructions file published in the GitHub repository Laotree/verify-networking-plugin (14 stars, last pushed 1mo ago), licensed MIT. It adds 1,659 tokens to every session, about $0.0083 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 2026-08-30.