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-cli-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-cli-runtime)<a href="https://agentmods.dev/skills/airtaxi/lidguard/lidguard-cli-runtime"><img src="https://agentmods.dev/badge/skills/airtaxi/lidguard/lidguard-cli-runtime.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 | $0.00057 | $0.04080 |
| Opus 5 | $0.00028 | $0.02040 |
| Sonnet 5 | $0.00011 | $0.00816 |
| Haiku 4.5 | $0.00006 | $0.00408 |
Grade B, and why
lidguard-cli-runtime scanned grade B with 1 finding 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Do not add a `sudo -v` prepare command; sudo credential caches are tty/timeout scoped and are not a reliable basis for long-running agent protection. How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LidGuard CLI Runtime
Command Routing
- Parse
help,start,stop,remove-pre-suspend-webhook,remove-post-session-end-webhook,remove-closed-lid-stop-follow-up-webhook,remove-session,status,live-status,settings,cleanup-orphans,current-lid-state,current-monitor-count,current-temperature,suspend-history,claude-hook,claude-hooks,copilot-hook,copilot-hooks,codex-hook,codex-hooks,opencode-hook,opencode-hooks,hook-status,hook-install,hook-remove,hook-events,mcp-status,mcp-install,mcp-remove,provider-mcp-status,provider-mcp-install,provider-mcp-remove,preview-system-sound,preview-current-sound,mcp-server, andprovider-mcp-server. - In Windows builds, additionally parse
wsl-hook-status,wsl-hook-install,wsl-hook-remove,wsl-codex-hooks,wsl-claude-hooks,wsl-copilot-hooks,wsl-opencode-hooks,wsl-mcp-status,wsl-mcp-install,wsl-mcp-remove,wsl-codex-mcp-status,wsl-codex-mcp-install,wsl-codex-mcp-remove,wsl-claude-mcp-status,wsl-claude-mcp-install,wsl-claude-mcp-remove,wsl-copilot-mcp-status,wsl-copilot-mcp-install,wsl-copilot-mcp-remove,wsl-opencode-mcp-status,wsl-opencode-mcp-install,wsl-opencode-mcp-remove,wsl-provider-mcp-status,wsl-provider-mcp-install, andwsl-provider-mcp-remove. - WSL management commands are Windows-only and must not appear in Linux or macOS routing or help output.
- WSL management commands accept optional
--distro <name>. When present, pass the distro through towsl.exe --distribution <name>; when absent, do not pass a distro so WSL uses its default distro. - Before any WSL management command does provider work, verify that
wsl.exeis usable and that the selected/default distro can execute a trivial command. - In Linux builds, additionally parse
linux-permission status,linux-permission check,linux-permission install, andlinux-permission remove. - Do not include Linux permission commands in Windows routing or help output.
- In macOS builds, additionally parse
macos-permission status,macos-permission check,macos-permission install, andmacos-permission remove. - Do not include macOS permission commands in Windows or Linux routing or help output.
- Make
helpprint a categorized command overview with short descriptions. - Make
help <command>print focused detailed help for one command or recognized command alias. - Make
<command> --helpuse the same help metadata and return before target command validation or command-specific work. - Include
opencodeanywhere help text lists supported first-party providers forstart,stop,remove-session, hook management, MCP management, and WSL management. - Load persisted default settings and send them with the start IPC request for
start, theUserPromptSubmitpath incodex-hookandclaude-hook, theuserPromptSubmittedpath incopilot-hook, and thechat.messagepath inopencode-hook. - Use the named-pipe runtime client for
start,stop,remove-session,status,settings, andcleanup-orphansrequests.
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.
- 4d ago Changed 81bcc42f6ede
- 8d ago First seen · 195 lines · 57 tokens per session scan B 33d693f3449c
lidguard-cli-runtime is a skill published in the GitHub repository airtaxi/LidGuard (10 stars, last pushed 7d ago), licensed MIT. It adds 57 tokens to every session and 4,080 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.