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.
curl -O https://raw.githubusercontent.com/airtaxi/LidGuard/master/.codex/skills/lidguard-product-runtime/SKILL.mdgit clone --depth 1 https://github.com/airtaxi/LidGuardWrote 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/skills/airtaxi/lidguard/lidguard-product-runtime)<a href="https://agentmods.dev/skills/airtaxi/lidguard/lidguard-product-runtime"><img src="https://agentmods.dev/badge/skills/airtaxi/lidguard/lidguard-product-runtime/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.
<a href="https://agentmods.dev/skills/airtaxi/lidguard/lidguard-product-runtime"><img src="https://agentmods.dev/badge/skills/airtaxi/lidguard/lidguard-product-runtime.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00053 | $0.01009 |
| Opus 5 | $0.00026 | $0.00504 |
| Sonnet 5 | $0.00011 | $0.00202 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
lidguard-product-runtime 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 11d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LidGuard Product Runtime
Overview
Use this skill as the lightweight entry point for LidGuard runtime behavior. For detailed work, load only the narrow runtime skill that matches the task.
- Power management, lid policy, suspend eligibility, and Emergency Hibernation: read
.codex/skills/lidguard-power-runtime/SKILL.md. - Active session lifecycle, soft-locking, transcript activity, process watching, runtime cleanup, and session-end webhook semantics: read
.codex/skills/lidguard-session-runtime/SKILL.md. - CLI command routing, settings defaults, permission commands, examples, suspend history, and failure modes: read
.codex/skills/lidguard-cli-runtime/SKILL.md. - Regular MCP server tools and model-managed Provider MCP runtime behavior: read
.codex/skills/lidguard-mcp-runtime/SKILL.md. - Provider hook installation, provider-specific payloads, and provider deployment behavior: read
.codex/skills/lidguard-provider-integrations/SKILL.md.
Product Goal
LidGuard is a Windows-first utility with systemd/logind Linux support and macOS support for long-running local AI coding agents such as Codex, Claude Code, GitHub Copilot CLI, and OpenCode.
The goal is to keep the supported local system awake while at least one tracked agent session still needs protection, then restore the user's original power policy after the session ends or becomes suspend-eligible.
- Agent sessions start through provider hooks or Provider MCP tools.
- LidGuard detects and tracks active sessions.
- Claude Code, GitHub Copilot CLI, and OpenCode sessions can enter a runtime-managed soft-lock state when provider notifications or events show the agent is waiting on user input.
- Codex, Claude Code, GitHub Copilot CLI, OpenCode, and Provider MCP sessions can also be soft-locked through runtime policy or MCP tools when autonomous work has paused.
- While at least one non-soft-locked session is active, LidGuard applies platform keep-awake protection.
- If every remaining active session is soft-locked, LidGuard releases temporary keep-awake protection, restores temporary lid policy changes, and starts the configured suspend flow only when the lid is closed and no suspend-blocking visible display monitors remain attached.
- If a session has no activity after the configured session timeout, LidGuard transitions it to the soft-locked state and applies the same keep-awake release flow used for normal soft-lock operations.
- When sessions stop, all temporary power settings must be restored to the user's original values.
- After the last active session stops, LidGuard should request suspend when the laptop lid is closed and no suspend-blocking visible display monitors remain attached to the desktop.
- If active sessions remain but all of them are soft-locked, LidGuard should follow the same suspend path without waiting for stop hooks.
- The suspend mode remains user-selectable: Sleep by default, Hibernate optional.
- The post-stop suspend delay remains user-selectable: 10 seconds by default,
0for immediate suspend. - The inactive session timeout remains user-selectable: 12 minutes by default,
offoptional, and enabled values must be at least 1 minute. - Optional pre-suspend and post-session-end webhook URLs remain off by default and must not block cleanup beyond their configured timeout.
- While keep-awake protection is applied and the laptop lid is closed with no suspend-blocking visible display monitors remaining, optional Emergency Hibernation should request immediate hibernation when the configured thermal threshold is reached.
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.
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.
- 11d ago First seen · 51 lines · 53 tokens per session scan A 805eaa486409
lidguard-product-runtime is a skill published in the GitHub repository airtaxi/LidGuard (11 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 1,009 once invoked, about $0.0003 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.
Other skills, from other repositories
anti-sleep
Keep a Mac awake with caffeinate during long builds, downloads, or supervised automation runs.
aot-trimming
Guidelines for making .NET libraries and applications trimming-safe and Native AOT compatible. Covers the trimming/AOT model, the MSBuild properties that enable analysis (IsTrimmable, IsAotCompatible, PublishTrimmed, PublishAot), the trimming attributes (RequiresUnreferencedCode, RequiresDynamicCode…
community-research-insight
Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.
history-explorer
Inspect recent session conversation turns and meta-run history. Returns structured JSON summaries of turn counts, role distribution, tool usage, meta-skill executions, and co-occurrence patterns. Use this before running meta-skill-creator or when the user asks about recent history, past tool usage, or session activity.
senior-java
World-class Java and Spring Boot development skill for enterprise applications, microservices, and cloud-native systems. Expertise in Spring Framework, Spring Boot 3.x, Spring Cloud, JPA/Hibernate, and reactive programming with WebFlux. Includes project scaffolding, dependency management, security implementation, and…
data-analyst
Connects to databases, runs SQL queries, and analyzes datasets using code to provide actionable business insights.