infrahub-mcp: Instructions file for Codex

AGENTS.md

infrahub-mcp AGENTS.md is an instructions file for Codex, OpenCode from opsmill/infrahub-mcp. It costs 1,565 tokens per session, scanned A, original, Apache-2.0.

Project instructions for an MCP server that lets AI assistants read and, with approval, change infrastructure state through an audited interface. MCP is a standard way for an AI assistant to connect to external tools.

In plain words
What is it for?
Use it when developing, testing, documenting, or operating the Infrahub MCP server and its infrastructure tools.
Why use it?
It gives contributors the project’s technology choices, file layout, security expectations, and development commands in one place.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is opsmill/infrahub-mcp's own configuration. It tells Codex and OpenCode how to work on infrahub-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything infrahub-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to opsmill/infrahub-mcp. 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/opsmill/infrahub-mcp/stable/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/opsmill/infrahub-mcp

Made for: Codex, OpenCode.

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.

agentmods badge for infrahub-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/opsmill/infrahub-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/opsmill/infrahub-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/opsmill/infrahub-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/opsmill/infrahub-mcp/agents-md/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.

agentmods 80×15 button for infrahub-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/opsmill/infrahub-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/opsmill/infrahub-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,565 This file is loaded in full into every session.
When invoked 1,565 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01565 $0.01565
Opus 5.5 $0.00626 $0.00626
Sonnet 5.5 $0.00313 $0.00313
Haiku 4.5 $0.00156 $0.00156

Measured 27d ago against content hash c43e50cc78d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

infrahub-mcp 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 27d 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.

AGENTS.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Infrahub MCP Server

Connects AI assistants to Infrahub over the open MCP standard, so agents can read and (optionally) change infrastructure state through a consistent, audited, human-approved interface.

Tech Stack

  • Runtime: Python 3.13, FastMCP, Infrahub SDK, Pydantic 2, Starlette
  • Testing: pytest, pytest-asyncio
  • Linting: ruff, mypy, pylint, yamllint
  • Docs: Docusaurus (.mdx in docs/docs/), rumdl for markdown linting
  • Package Manager: uv

File Structure

  • src/infrahub_mcp/ — Library source code
    • tools/ — MCP tool implementations (gql, nodes, schema, session, write)
    • resources/ — MCP resources (branches, schema)
    • prompts/ — MCP prompt templates
    • middleware.py — Full middleware stack (logging, caching, auth, rate limiting, audit)
    • server.py — FastMCP server construction and ASGI app
    • config.py — ServerConfig via pydantic-settings
    • auth.py — OIDC provider factory and identity helpers
  • tests/ — Test suite
  • docs/ — User-facing documentation (Docusaurus)
  • dev/ — Internal developer documentation — see dev/README.md
  • .agents/ — AI agent commands and skills
  • .specify/ — Speckit scaffolding (templates, workflows, extensions)

Commands

uv sync                          # Install dependencies

uv run pytest                    # Run full test suite

uv run invoke format             # Auto-format with ruff
uv run invoke lint               # All linters (yaml, ruff, pylint, mypy)
uv run invoke lint-ruff          # Ruff only
uv run invoke lint-pylint        # Pylint only
uv run invoke lint-mypy          # MyPy type checking only
uv run invoke lint-yaml          # Yamllint only

uv run rumdl check docs/docs/    # Check markdown linting
uv run rumdl fmt docs/docs/      # Auto-fix markdown formatting
cd docs && npm run build         # Test documentation build

uv run pre-commit run            # Ruff + rumdl on staged files, Mypy on src/
uv run pre-commit install        # Optional: run those same hooks on every commit

Read the full file on GitHub · 122 lines

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.

  1. 27d ago Changed · +44 tokens per session c43e50cc78d5
  2. 1mo ago Changed · +8 lines · +118 tokens per session 25ff5c50fe34
  3. 1mo ago Changed · +11 lines · +294 tokens per session cbc2f25e3093
  4. 2mo ago First seen · 103 lines · 1,109 tokens per session scan A c394d7532f73

Subscribe to this mod's changes

infrahub-mcp AGENTS.md is an instructions file published in the GitHub repository opsmill/infrahub-mcp (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,565 tokens to every session, about $0.0063 per session on Opus 5.5. 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 2026-09-03.

Related

infrahub-mcp AGENTS.md compared with instructions from other repositories

infrahub-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
infrahub-mcp AGENTS.mdopsmill/infrahub-mcpInstructions file10yesterdayApache-2.0A1,565Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode