LidGuard: Skill for Codex

.codex/skills/lidguard-repo-workflow/SKILL.md

lidguard-repo-workflow is a skill for Codex from airtaxi/LidGuard. It costs 41 tokens per session (806 once invoked), scanned A, original, MIT.

A set of repository-specific instructions for working on the LidGuard codebase. It tells an agent which language to use, how to handle commits, when to build, and which local coding rules to read.

In plain words
What is it for?
Planning, editing, reviewing, testing, documenting, staging, and running tools in the LidGuard repository.
Why use it?
It prevents work from violating the project's established procedures or language and build constraints.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md; mentions Codex.

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 →

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/.codex/skills/lidguard-repo-workflow/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-repo-workflow

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/airtaxi/lidguard/lidguard-repo-workflow"><img src="https://agentmods.dev/badge/skills/airtaxi/lidguard/lidguard-repo-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 806 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 $0.00041 $0.00806
Opus 5 $0.00020 $0.00403
Sonnet 5 $0.00008 $0.00161
Haiku 4.5 $0.00004 $0.00081

Measured 12d ago against content hash e36487389003, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lidguard-repo-workflow 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 12d 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.

.codex/skills/lidguard-repo-workflow/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LidGuard Repository Workflow

Overview

Use this skill before every LidGuard task. AGENTS.md is only a router; the repository-local skills under .codex/skills are the authoritative project instructions.

Mandatory Rules

  • Respond in Korean. The user is a South Korean native speaker.
  • Never run git commit or git push unless the user explicitly requests it.
  • Before any user-requested commit, inspect recent commits and match the repository convention; LidGuard commit messages must be written in English.
  • When staging many files where only a few files must be excluded, stage everything first, then unstage only those few excluded files.
  • When using rg, use C:\Data\Utils\Path\rg.exe.
  • Do not run builds unless the user explicitly asks for one, except when the changes are huge.
  • If something is unclear or ambiguous during work, ask the user immediately and provide selectable choices when possible.
  • Before creating, modifying, reviewing, refactoring, or explaining C# code or project files, read .codex/skills/csharp-code-style/SKILL.md. If a global skill has the same name, use this local skill instead of the global one.
  • This repository is NativeAOT and trimming sensitive. Avoid APIs that trigger IL2026 / IL3050 warnings, and prefer AOT-safe overloads plus source-generated System.Text.Json serializers over reflection-driven or dynamic JSON helpers.
  • Windows native interop must stay centralized through CsWin32-generated APIs. Do not add direct [DllImport] / [LibraryImport], NativeLibrary / GetProcAddress, or manual COM vtable calls in project code unless CsWin32 or available metadata cannot express the API and the exception is documented in the local skills.
  • Microsoft.Windows.WDK.Win32Metadata is intentionally referenced only to let CsWin32 generate WDK-backed APIs such as NtQueryInformationProcess; keep it PrivateAssets="all" and do not use it as permission to add hand-written native declarations.
  • Persisted timestamps for sessions, runtime logs, hook logs, suspend history, backup state, notification data, and timestamped backup file names must be recorded from UTC sources such as DateTimeOffset.UtcNow; user-facing CLI and web output must convert stored timestamps to the current system local time immediately before display.

Read the full file on GitHub · 37 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. 12d ago First seen · 37 lines · 41 tokens per session scan A e36487389003

Subscribe to this mod's changes

lidguard-repo-workflow is a skill published in the GitHub repository airtaxi/LidGuard (11 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 806 once invoked, about $0.0002 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.