agentmods.dev

LidGuard: Skill for Codex

.agents/skills/lidguard-implementation-map/SKILL.md

lidguard-implementation-map is a skill for Codex from airtaxi/LidGuard. It costs 45 tokens per session (1,589 once invoked), scanned A, original, MIT.

A map of the LidGuard codebase and its design boundaries. It explains where shared logic belongs, how Windows, Linux, and macOS code is separated, and how the .NET application is organized.

In plain words
What is it for?
Use it when changing repository structure, feature ownership, platform files, project targets, or other architectural parts of LidGuard.
Why use it?
It reduces the risk of putting code in the wrong subsystem or breaking platform-specific builds and NativeAOT requirements.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is airtaxi/LidGuard's own configuration. It tells Codex how to work on LidGuard 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 LidGuard configures →

not rated 13repo 1mo ago A scan 45 tokens original MIT
View source ↗ airtaxi/LidGuard nuget.org
Reuse

Borrowing it

Nothing to install: this file belongs to airtaxi/LidGuard. 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/airtaxi/LidGuard/master/.agents/skills/lidguard-implementation-map/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/airtaxi/LidGuard

Made for: Codex.

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 lidguard-implementation-map

README.md
[![agentmods](https://agentmods.dev/badge/skills/airtaxi/lidguard/lidguard-implementation-map/github.svg)](https://agentmods.dev/skills/airtaxi/lidguard/lidguard-implementation-map)
Your own site
<a href="https://agentmods.dev/skills/airtaxi/lidguard/lidguard-implementation-map"><img src="https://agentmods.dev/badge/skills/airtaxi/lidguard/lidguard-implementation-map/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 lidguard-implementation-map

Your own site · 80×15
<a href="https://agentmods.dev/skills/airtaxi/lidguard/lidguard-implementation-map"><img src="https://agentmods.dev/badge/skills/airtaxi/lidguard/lidguard-implementation-map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,589 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 $0.00045 $0.01589
Opus 5.5 $0.00018 $0.00636
Sonnet 5.5 $0.00009 $0.00318
Haiku 4.5 $0.00005 $0.00159

Measured 2mo ago against content hash 13024dbb1cbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lidguard-implementation-map 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 2mo 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.

.agents/skills/lidguard-implementation-map/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LidGuard Implementation Map

Scope

Use this skill for repository shape, subsystem ownership, and architectural constraints. Keep release-phase tracking, completed-component inventories, and missing-work lists out of this file.

Repository Shape

  • LidGuard
    • .NET 10 console app targeting net10.0.
    • Visual Studio platform switching uses RID-shaped solution/project platforms windows-x86, windows-x64, windows-arm64, linux-x64, linux-arm64, macos-x64, and macos-arm64; the project maps those to RuntimeIdentifier and LidGuardTargetPlatform.
    • Standalone hook-facing CLI plus in-process headless runtime and stdio MCP server hosting.
    • Common, platform-neutral models and policies live in feature folders such as Sessions, Settings, Power, Services, Results, and Processes.
    • Shared provider/hook utilities live under Hooks in regular *.cs files.
    • Windows-specific runtime/process/power implementations live in *.windows.cs.
    • Linux-specific systemd/logind, /proc, and /sys implementations live in *.linux.cs.
    • macOS-specific runtime/process/power implementations live in *.macOS.cs.
    • Platform-specific files are compiled according to LidGuardTargetPlatform, which is selected from Visual Studio Platform, then RID, then current host OS.
    • Nullable is intentionally not enabled in the csproj.
    • ImplicitUsings is enabled.
    • NativeAOT/trimming compatibility flags are enabled.
    • Uses CsWin32 with CsWin32RunAsBuildTask=true and DisableRuntimeMarshalling=true for AOT compatibility.
    • Uses root namespace LidGuard and assembly/apphost name lidguard.
    • Prepared for .NET 10 RID-specific NativeAOT .NET tool distribution as NuGet package lidguard with tool command lidguard.
    • Package RID support is prepared for win-x64, win-x86, win-arm64, linux-x64, linux-arm64, osx-x64, and osx-arm64, but the release workflow excludes linux-arm64 because of the NativeAOT cross-linking known issue documented in the .NET Tool Package Guidelines.
    • Uses a named pipe to send start, stop, remove-session, status, settings, and cleanup-orphans requests to the runtime.
    • Hosts the stdio MCP server through the mcp-server subcommand.
    • Stores default settings JSON under the platform local application data directory, such as %LOCALAPPDATA%\LidGuard\settings.json on Windows, ~/.local/share/LidGuard/settings.json on typical Linux desktops, or the .NET local application data path on macOS.
  • LidGuard.Notifications
    • .NET 10 ASP.NET Core Razor Pages app targeting net10.0.
    • Receives LidGuard pre-suspend, post-session-end, and ask-before-sleep reply webhooks and sends browser Web Push notifications to subscribed clients.
    • Stores subscriptions, webhook events, ask-before-sleep reply state, and delivery attempts in SQLite.
    • Uses server-side VAPID settings; VAPID private keys and access tokens must never be committed.
  • LidGuard.slnx
    • Root solution file including LidGuard and LidGuard.Notifications.

Read the full file on GitHub · 80 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 80 lines · 45 tokens per session scan A 13024dbb1cbe

Subscribe to this mod's changes

lidguard-implementation-map is a skill published in the GitHub repository airtaxi/LidGuard (13 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,589 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 2026-08-31.

Backend and APIsC# and .NETLanguagescaffeinatehibernatelid-closemcpnativeaotpower-management
Related

lidguard-implementation-map compared with skills from other repositories

lidguard-implementation-map next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lidguard-implementation-mapairtaxi/LidGuardSkill131mo agoMITA45Codex
agui-dotnet-streaming-chatag-ui-protocol/ag-uiSkill17kyesterdayMITA223Claude Code
azure-maps-search-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA91Claude Code
azure-mgmt-apicenter-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA97Claude Code
azure-ai-voicelive-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA92Claude Code
create-datadriven-aspnetcoredotnet/skillsSkill5.8kyesterdayMITA147Claude Code
omnistudio-callable-apex-generateforcedotcom/sf-skillsSkill1.1k2d agoApache-2.0A176Claude Code, Codex