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/roypadina/languard/claude-mdgit clone --depth 1 https://github.com/roypadina/LanGuardWrote 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/roypadina/languard/claude-md)<a href="https://agentmods.dev/instructions/roypadina/languard/claude-md"><img src="https://agentmods.dev/badge/instructions/roypadina/languard/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 5.1 | $0.01190 | $0.01190 |
| Opus 5 | $0.00595 | $0.00595 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
LanGuard 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 6d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LanGuard
macOS menu-bar app. Turns Wi-Fi off when a wired LAN link goes up, on when it
goes down. Replaces the old shell com.roy.wifitoggle LaunchAgent (the app removes it
on first launch).
Layout
LanGuard/— app target (LanGuardApp.swift):MenuBarExtra+ SettingsWindow,AppDelegatestartsAppModel.LanGuardPackage/Sources/LanGuardFeature/— all logic (modular, unit-tested):InterfaceCatalog— enumerate + classify Ethernet/Wi-Fi via SystemConfiguration.isVirtual(bsdName:displayName:)flags bridge/VPN/VM/tunnel adapters (pure, tested).NetworkMonitor—SCDynamicStorecallbacks (link/IPv4) +NSWorkspacesleep/wake; per-interface link reads (SCkSCPropNetLinkActive, ifconfig fallback). Flap guard: ignores link changes while asleep (willSleepNotification→suspended), waits a settle interval afterdidWakeNotificationbefore evaluating once, and debounces callback bursts/brief flaps (1.5s). Stops a docked Mac's Ethernet dropping on sleep + returning on wake from looking like a real unplug→replug.WiFiController— CoreWLANsetPower/powerOn(no sudo, no shell).Notifier—UNUserNotificationCenterwrapper; banners on Wi-Fi toggle (needs OS permission, requested on launch).Log— opt-in file logger. WhendebugLoggingEnabled(Settings → Debug) is on, appends timestamped events to~/Library/Logs/LanGuard/languard.log(rotates at ~1MB, one backup).Log.writeis a no-op while off.revealInFinder()/clear()back the Settings buttons. Instrumented across start / evaluate / edges / setWiFiPower / sleep-wake so users can capture + send a log.MenuIcon—MenuState(lan/wifi/paused, pure mapping) +MenuIconStyle(icon / icon+label / label) +MenuBarLabelview used as the MenuBarExtra label.ToggleEngine— edge-based decision logic, dependencies injected → testable.AppSettings— UserDefaults. Physical wired + Wi-Fi = opt-out (disabledWired/disabledWiFi); virtual wired = opt-in (enabledVirtual, off by default).notificationsEnabled,menuIconStyle.LoginItem/LegacyCleanup— SMAppService login item (self-healing, see below); removes legacy LaunchAgent.AppModel— wires everything; singletonAppModel.shared.setWiFiPoweris idempotent — only toggles interfaces whose power actually differs and only posts the banner when something really changed.Views—MenuContent(menu),ConfigView(settings window; virtual adapters get a "virtual" badge).
Config/— xcconfig + entitlements. Un-sandboxed (CoreWLAN power + launchctl), ad-hoc signed,LSUIElement=YES(no Dock icon).
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.
- 6d ago First seen · 56 lines · 1,190 tokens per session scan A d99f57b9210d
LanGuard CLAUDE.md is an instructions file published in the GitHub repository roypadina/LanGuard (22 stars, last pushed 2mo ago), licensed MIT. It adds 1,190 tokens to every session, about $0.0060 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
OnlySwitch AGENTS.md
Instructions for jacklandrin/OnlySwitch, covering onlyswitch agent guidance, workflow, context routing and project-specific working rules.
PokeTokenBar CLAUDE.md
Claude Code instructions for chattymin/PokeTokenBar, covering poketokenbar — claude 프로젝트 지침, 참조 문서 (필요할 때 읽는다), 기여 언어 규약 (오픈소스 대비 — english first), 릴리스 (자연어 트리거) and 확장 규약 (새 프로바이더/툴 추가 시).
TokenBar AGENTS.md
AGENTS.md instructions for Nanako0129/TokenBar, covering tokenbar agent routing, read order, invariants, authorization boundary and handoff.
TokenBar CLAUDE.md
Claude Code instructions for Nanako0129/TokenBar: Read AGENTS.md first, then docs/knowledge/README.md and the task-specific canonical document it routes to. If .agent-local/CLAUDE.md exists, read it after the canonical documents as additive machine-local guidance only; it must not override the canonical architecture…
barkeep AGENTS.md
AGENTS.md instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.
cai CLAUDE.md
Instructions for cai-layer/cai, covering claude.md, what is cai?, design system, build & run and dev.