safedep

safedep/vet

Cursor rule Cursor

Always use vet-mcp to vet any open source library package suggested by AI generated code before installation. Follow the rules below to use vet-mcp.

safedep/vet

Cursor rule Cursor

Always use TypeScript for new files.

safedep/vet

Settings file Claude Code

MCP configuration declaring 1 server: local-tool.

safedep/vet

MCP server Claude CodeCodexCursor +2

MCP server "safedep" as configured in safedep/vet. Runs locally from the @safedep/mcp npm package. Needs 1 environment variable to run.

safedep/vet

MCP server Claude CodeCodexCursor +2

MCP server "postgres" as configured in safedep/vet. Runs locally from the @mcp/postgres npm package. Needs 1 environment variable to run.

safedep/vet

MCP server Claude CodeCodexCursor +2

MCP server "vet-mcp" as configured in safedep/vet. Runs in Docker (ghcr.io/safedep/vet:v1.12.13).

safedep/gryph

Skill Claude CodeCodex

Use when working on Gryph's AARM security layer or policy engine. Trigger this whenever the user changes code under aarm/ or cli/policy.go, or works on policy evaluation, the PDP, policy rules, CEL conditions, receipts and the receipt hash chain, receipt signing, the context accumulator, approvals, deferrals, identity…

safedep/gryph

Skill Claude CodeCodex

Use when adding support for a new AI coding agent to Gryph, or when changing how an existing agent adapter is wired. Trigger this whenever the user wants to integrate a new agent (for example Claude Code, Cursor, Gemini, Codex, Windsurf, or any other tool), add a new adapter package under agent/, wire agent hook…

safedep/gryph

Skill Claude CodeCodex

Use when a human wants help to author or change a Gryph security policy that governs what an AI coding agent may do, often with an agent's help. Trigger whenever the user wants Gryph to block, allow, warn on, or require approval for an agent action, wants to write or change a policy rule, asks how to match a tool…

safedep/gryph

Instructions file CodexOpenCode

Instructions for safedep/gryph, covering gryph, build, architecture, key entry points and notes.

safedep/gryph

Instructions file

Instructions for safedep/gryph, a project described as: Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more.