Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/aipotheosis-labs/gate22/agents-mdgit clone --depth 1 https://github.com/aipotheosis-labs/gate22Wrote 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/instructions/aipotheosis-labs/gate22/agents-md)<a href="https://agentmods.dev/instructions/aipotheosis-labs/gate22/agents-md"><img src="https://agentmods.dev/badge/instructions/aipotheosis-labs/gate22/agents-md.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 | $0.00417 | $0.00417 |
| Opus 5 | $0.00209 | $0.00209 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
gate22 AGENTS.md 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 5d 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.
What it actually says
AGENTS.md
This document provides coding agents with detailed context about the Gate22 repository structure, build processes, testing procedures, and conventions.
Project Overview
Gate22 is an open-source MCP (Model Context Protocol) Gateway and Control Plane for AI governance.
- Backend: Python/FastAPI-based service that powers the control plane, MCP hosting, and Virtual MCP servers
- Frontend: Next.js 15 TypeScript application for the management portal
Repository Structure
gate22/
├── backend/ # Python backend services
│ ├── aci/ # Main application package
│ │ ├── alembic/ # Database migrations
│ │ ├── cli/ # Internal Admin CLI commands
│ │ ├── common/ # Shared utilities
│ │ ├── control_plane/ # FastAPI service for the control plane
│ │ ├── mcp/ # FastAPI service for the MCP servers (bundle)
│ │ └── virtual_mcp/ # FastAPI service for the Virtual MCP servers
│ ├── mcp_servers/ # MCP server definitions
│ ├── virtual_mcp_servers/ # Virtual MCP server definitions
│ ├── pyproject.toml # Python dependencies
│ └── compose.yml # Docker Compose configuration
├── frontend/ # Next.js frontend application
│ ├── src/
│ │ ├── app/ # Next.js App Router pages
│ │ ├── features/ # Feature-based modules
│ │ ├── components/ # Shared UI components
│ │ └── lib/ # Utilities and shared logic
│ └── package.json # Node.js dependencies
└── .pre-commit-config.yaml # Pre-commit hooks configuration
Backend
Code Style & Quality
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.
- 5d ago First seen · 41 lines · 417 tokens per session scan A f3ffe5896103
gate22 AGENTS.md is an instructions file published in the GitHub repository aipotheosis-labs/gate22 (178 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 417 tokens to every session, about $0.0021 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 2026-08-30.
Other instructions, from other repositories
bifrost AGENTS.md
AGENTS.md instructions for maximhq/bifrost, covering agents.md — bifrost ai gateway, what is bifrost?, repository layout, go workspace and build, test & dev commands.
decapod AGENTS.md
AGENTS.md instructions for DecapodLabs/decapod, covering agents.md — universal agent contract, mandatory orientation, mandatory prompt safety gate, mandatory initialization and control-plane first loop.
decapod CLAUDE.md
Claude Code instructions for DecapodLabs/decapod, covering claude.md - agent entrypoint, orientation & documentation, mandatory prompt safety gate, project context and quick start.
Guardrails AGENTS.md
AGENTS.md instructions for NVIDIA-NeMo/Guardrails, covering agents.md, agent skills, quick rules, repository map and setup.
Guardrails CLAUDE.md
Claude Code instructions for NVIDIA-NeMo/Guardrails, a project described as: NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
decapod GEMINI.md
Gemini CLI instructions for DecapodLabs/decapod, covering gemini.md - agent entrypoint, orientation & documentation, mandatory prompt safety gate, project context and quick start.