skarn-security

skarn-security/agent-guard

Plugin Claude Code

Skarn security guard for AI coding assistants.

skarn-security/agent-guard

Instructions file Gemini CLI

Instructions for skarn-security/agent-guard: This extension adds a local skarn MCP server and the skarn-audit skill. The server runs on the user's machine, makes no network call, and exposes four tools.

skarn-security/agent-guard

Skill Claude CodeCodex

Audit this machine's AI coding sessions and assistant configs with skarn. Use when the user says scan this with skarn, run skarn, or skarn audit; asks whether a secret leaked into an AI coding session; wants an assistant config (hooks, MCP servers, permissions, plugins) vetted; or asks whether a Claude Code, Codex…

skarn-security/agent-guard

Plugin Claude Code

Real-time guard on five Claude Code pre-execution hook events (tool calls, permission decisions, submitted and expanded prompts, and subagent creation) plus a response-end advisory that flags an action leaking a secret, installing a malicious package, or exfiltrating data, plus the skarn-audit skill (scan sessions and.

skarn-security/agent-guard

MCP server Claude CodeCodexCursor +2

MCP server "skarn" as configured in skarn-security/agent-guard. Launched with skarn mcp.

skarn-security/agent-guard

Hook

Runs before the agent uses a tool for Bash, WebFetch, WebSearch, Write, Edit, MultiEdit, NotebookEdit and mcp__.* tool calls, running skarn guard --guard-mode audit. From skarn-security/agent-guard.

skarn-security/agent-guard

Hook

Runs when the agent asks permission for an action for Bash, WebFetch, WebSearch, Write, Edit, MultiEdit, NotebookEdit and mcp__.* tool calls, running skarn guard --agent claude --guard-mode audit. From skarn-security/agent-guard.

skarn-security/agent-guard

Hook

Runs when you submit a prompt, before the agent sees it, running skarn guard --guard-mode audit. From skarn-security/agent-guard.

skarn-security/agent-guard

Hook

Runs to expand your prompt before the agent sees it, running skarn guard --guard-mode audit. From skarn-security/agent-guard.

skarn-security/agent-guard

Hook

Runs on the TaskCreated event, running skarn guard --guard-mode audit. From skarn-security/agent-guard.

skarn-security/agent-guard

Hook

Runs when the agent finishes a response, running skarn guard --guard-mode audit. From skarn-security/agent-guard.

skarn-security/agent-guard

Plugin Claude Code

Real-time pre-execution guard that blocks AI tool calls leaking a secret, installing a malicious package, or exfiltrating data, plus the skarn-audit skill (scan sessions and vet configs, redacted). Backed by the Skarn detection engine. Audit mode reports only.

skarn-security/agent-guard

Plugin Claude Code

Skill: reconstruct what you worked on from your AI coding sessions (recent, stats, redacted export). Reads session content, so it ships separately from skarn-guard. Backed by the Skarn session engine.

skarn-security/agent-guard

Skill Claude CodeCodex

Reconstruct what was worked on from past AI coding sessions with skarn. Use when the user asks what they worked on; wants a standup, handover, or timesheet built from their sessions; asks which sessions touched a project or topic; wants token and cost stats; or says skarn recall. Not for security questions (use…

skarn-security/cursor-plugin

Skill Claude CodeCodex

Audit this machine's AI coding sessions and assistant configs with skarn. Use when the user says scan this with skarn, run skarn, or skarn audit; asks whether a secret leaked into an AI coding session; wants an assistant config (hooks, MCP servers, permissions, plugins) vetted; or asks whether a Claude Code, Codex…

skarn-security/skarn-dist

MCP server Claude CodeCodexCursor +2

Scans AI coding sessions and assistant configs for leaked secrets and risky hooks; local, redacted. Runs locally from the @skarn-security/skarn npm package.