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.
npx agentmods add instructions/laotree/verify-networking-plugin/claude-mdgit clone --depth 1 https://github.com/Laotree/verify-networking-pluginWrote 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/laotree/verify-networking-plugin/claude-md)<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>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 | $0.01659 | $0.01659 |
| Opus 5 | $0.00830 | $0.00830 |
| Sonnet 5 | $0.00332 | $0.00332 |
| Haiku 4.5 | $0.00166 | $0.00166 |
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.
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 |
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.
- 4d ago First seen · 159 lines · 1,659 tokens per session scan A 365c9c1e33c7
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.
Other instructions, from other repositories
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
agentgateway copilot-instructions.md
Copilot instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.
terminal-browser AGENTS.md
AGENTS.md instructions for zenbu-labs/terminal-browser, a project described as: A browser inside your terminal.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.