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-mcp-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-mcp-runtime)<a href="https://agentmods.dev/skills/airtaxi/lidguard/lidguard-mcp-runtime"><img src="https://agentmods.dev/badge/skills/airtaxi/lidguard/lidguard-mcp-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-mcp-runtime"><img src="https://agentmods.dev/badge/skills/airtaxi/lidguard/lidguard-mcp-runtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.01777 |
| Opus 5 | $0.00024 | $0.00889 |
| Sonnet 5 | $0.00010 | $0.00355 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
lidguard-mcp-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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LidGuard MCP Runtime
Regular MCP Server
- Host the regular stdio MCP server through
lidguard mcp-server. mcp-statusinspects the provider's global/user MCP configuration and reports whether thelidguardserver entry is present and still points at the current LidGuard executable plusmcp-server.mcp-installandmcp-removeregister or remove the user/global LidGuard stdio MCP server namedlidguardfor Codex, Claude Code, GitHub Copilot CLI, and OpenCode.mcp-installrefreshes an existing managed LidGuard MCP registration, including one that points at an older LidGuard executable, by removing the existing provider entry first, then reinstalling it with the current command and arguments.- Windows WSL MCP management mirrors regular MCP management with WSL-side provider CLIs and config files, but the registered command must be the current Windows
lidguard.execonverted throughwslpath. Supported commands arewsl-mcp-status/install/remove [codex|claude|copilot|opencode|all]pluswsl-codex-mcp-*,wsl-claude-mcp-*,wsl-copilot-mcp-*, andwsl-opencode-mcp-*aliases. - OpenCode MCP management edits the OpenCode JSON/JSONC config directly under the
mcpobject using a localcommandarray instead of calling an OpenCode CLI registration command. OpenCode MCP status should only report the managed server as installed when the entry istype = local, not disabled, points at the current LidGuard executable, and containsmcp-serverin the command array. - Prefer the current
lidguard.exepath over the Windows.cmdshim when registering stdio MCP servers, because shim wrapper processes can remain visible under MCP clients and should not be mistaken for agent work. - Expose
get_settings_status,list_sessions,update_settings,remove_session,set_session_soft_lock, andclear_session_soft_lock. - Make
list_sessionsreturn the active session list plus runtime lid/session state without the full settings payload. - Make
update_settingsaccept multiple setting fields in a single request and persist them together. - Expose inactive session timeout through
sessionTimeoutMinutes, acceptingoffor an enabled minute count of at least 1. - Expose server runtime cleanup delay through
serverRuntimeCleanupDelayMinutes, acceptingoffto keep the runtime alive,0for immediate exit, or a positive minute count to wait. - Expose post-session-end webhook URL through
postSessionEndWebhookUrl, accepting an empty string to clear it. - Expose the ask-before-sleep reply webhook URL through
closedLidStopFollowUpWebhookUrl, accepting an empty string to clear it. - Expose ask-before-sleep reply wait through
closedLidStopFollowUpDelaySeconds, defaulting to180;0disables reply waiting, and values1through19are saved but become configuration errors when the URL is configured. - Expose ask-before-sleep reply wait sound through
closedLidStopFollowUpSound, acceptingoff, an empty string, a supported system sound name, or a playable.wavpath. - Expose ask-before-sleep reply wait sound volume override through
closedLidStopFollowUpSoundVolumeOverridePercent, acceptingoffor an enabled percent from 1 through 100. - Expose repeated ask-before-sleep reply behavior through
repeatClosedLidStopFollowUp, defaulting totrue. - Make
remove_sessionmanually remove active sessions by session identifier and optionally narrow removal to one provider and one MCP provider name. - Keep
set_session_soft_lockandclear_session_soft_lockgeneral-purpose by accepting provider and session identifier inputs, so non-MCP providers can also use MCP-driven soft-lock control when they can supply those values. - Use the same named-pipe client and settings store for MCP settings updates that the CLI uses.
- Do not launch
run-serverfrom MCP settings updates when no runtime is listening. - Keep MCP server logging on stderr so stdio tool traffic remains clean.
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 · 83 lines · 49 tokens per session scan A 8aa68dd881d2
lidguard-mcp-runtime is a skill published in the GitHub repository airtaxi/LidGuard (11 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 1,777 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.
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.