What is lidguard-provider-integrations?

A reference for connecting LidGuard to coding-agent providers such as Codex, Claude Code, GitHub Copilot CLI, and OpenCode. It covers provider-specific hooks, MCP registration, payloads, and deployment details.

Use it when adding or changing provider hooks, Provider MCP support, installation/status/removal commands, or deployment notes.

It helps integrations use the correct provider names, session handling, commands, and configuration instead of treating every agent as identical.

How airtaxi/LidGuard configures Claude Code and Codex

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-provider-integrations/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/airtaxi/LidGuard

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/airtaxi/lidguard/lidguard-provider-integrations/github.svg)](https://agentmods.dev/skills/airtaxi/lidguard/lidguard-provider-integrations)

Your own site

<a href="https://agentmods.dev/skills/airtaxi/lidguard/lidguard-provider-integrations"><img src="https://agentmods.dev/badge/skills/airtaxi/lidguard/lidguard-provider-integrations/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/airtaxi/lidguard/lidguard-provider-integrations"><img src="https://agentmods.dev/badge/skills/airtaxi/lidguard/lidguard-provider-integrations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,216 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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.07216
Opus 5	$0.00031	$0.03608
Sonnet 5	$0.00012	$0.01443
Haiku 4.5	$0.00006	$0.00722

Measured 12d ago against content hash 7045620de627, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

lidguard-provider-integrations 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-provider-integrations/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LidGuard Provider Integrations

AgentProvider Enum

File: LidGuard/Sessions/AgentProvider.cs.
Enum ordering: Unknown = -1, Codex = 0, then Claude, GitHubCopilot, and OpenCode in increasing order, then Custom, then Mcp.
When adding a new named provider, insert it immediately before Custom with the next consecutive integer value.
The [JsonConverter(typeof(JsonStringEnumConverter<AgentProvider>))] attribute means all serialization uses string names, so the integer values are only for ordering and do not affect persistence. Renumbering existing members is safe as long as every reference uses the named enum member.

Provider MCP Mapping

Generic Provider MCP

Provider enum: AgentProvider.Mcp.
Provider sessions are distinguished by both sessionId and providerName.
provider_start_session generates a stable Provider MCP sessionId by taking the first 8 lowercase hexadecimal characters from a new GUID and returns that value to the model.
The model must keep reusing the exact sessionId returned by provider_start_session until the session is truly complete.
Provider MCP install/remove/status commands are lidguard provider-mcp-status --config <json-path>, lidguard provider-mcp-install --config <json-path> --provider-name <name>, and lidguard provider-mcp-remove --config <json-path>.
Provider MCP config is edited directly as JSON and does not reuse the Codex, Claude Code, or GitHub Copilot CLI-specific MCP registration flows.
Provider MCP server command: lidguard provider-mcp-server --provider-name <name>.
Provider MCP start tool: provider_start_session.
Provider MCP stop tool: provider_stop_session.
Provider MCP soft-lock tools: provider_set_soft_lock and provider_clear_soft_lock.
provider_start_session should be described to the model as a brand-new-session call that auto-generates the reusable sessionId.
provider_stop_session should be described to the model as a pre-turn-end call only when the work is truly complete.
provider_set_soft_lock should explain the soft-lock concept and instruct the model to call it before ending a turn that is about to wait for user input. The description must also explain that the tool cannot end the turn on the model's behalf.
provider_clear_soft_lock should instruct the model to resume the earlier returned sessionId after the user replies, instead of minting a new session.
Because all Provider MCP behavior depends on model compliance, do not promise or document it as guaranteed behavior.
Ask-before-sleep reply continuation is not implemented for Provider MCP and must never be described as supported there.

Read the full file on GitHub · 197 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.

agents/openai.yaml 130 B

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.

12d ago First seen · 197 lines · 62 tokens per session scan A 7045620de627

Subscribe to this mod's changes

lidguard-provider-integrations is a skill published in the GitHub repository airtaxi/LidGuard (11 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 7,216 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.

Building agents caffeinate hibernate lid-close mcp nativeaot power-management

anti-sleep

Keep a Mac awake with caffeinate during long builds, downloads, or supervised automation runs.

sickn33/agentic-awesome-skills · 22 tokens

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…

Aaronontheweb/dotnet-skills · 181 tokens

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.

clawdotnet/openclaw.net · 41 tokens

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.

clawdotnet/openclaw.net · 65 tokens

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…

benchflow-ai/skillsbench · 65 tokens

data-analyst

Connects to databases, runs SQL queries, and analyzes datasets using code to provide actionable business insights.

clawdotnet/openclaw.net · 25 tokens

LidGuard: Skill for Claude Code