What is aiops-mcp AGENTS.md?

A set of AGENTS.md instructions for the aiops-mcp repository, an AI-operations server for monitoring and managing infrastructure. It documents the repository layout, operating rules, and build and test guidance.

It is for guiding changes to the aiops-mcp codebase, including its execution, data, telemetry, infrastructure adapters, tools, and audit components.

It gives coding agents project-specific context and constraints, helping them work consistently within the repository’s security and governance rules.

How rmednitzer/aiops-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to rmednitzer/aiops-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/rmednitzer/aiops-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/rmednitzer/aiops-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/rmednitzer/aiops-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/rmednitzer/aiops-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/rmednitzer/aiops-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rmednitzer/aiops-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/rmednitzer/aiops-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rmednitzer/aiops-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 677 This file is loaded in full into every session.

When invoked 677 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.

Model	Per session	Once invoked
Fable 5.1	$0.00677	$0.00677
Opus 5.5	$0.00271	$0.00271
Sonnet 5.5	$0.00135	$0.00135
Haiku 4.5	$0.00068	$0.00068

Measured 2mo ago against content hash f9e0c2b6b1ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aiops-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 2mo 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Short operating spec for aiops-mcp (product: praxis). The design reference is docs/architecture.md; the behavior overlay is CLAUDE.md.

One-line

A self-contained, security-first unified AI-operations MCP server: a live bitemporal fleet model, a drift engine, and a tiered audited actuator.

Repo map

src/praxis/execution/ the single audited, tier-aware execution core (patterns, policy, redaction, audit, contract, runner). patterns.py is the sole security-review file.
src/praxis/model/, src/praxis/store/ the bitemporal fact model and the pluggable store (sqlite default, postgres+age production) behind one Protocol.
src/praxis/collectors/, src/praxis/drift/ read-only telemetry into facts, and observed-vs-desired diffing.
src/praxis/actuation/ adapters that wrap ssh/opentofu/ansible/runbooks/ talosctl/redfish/cloud (DRY_RUN, then approve, then execute).
src/praxis/skills/, src/praxis/tools/ skills engine and the MCP tool surface; src/praxis/audit/ tamper-evident evidence.
docs/adr/, docs/stpa/, docs/backlog.md, docs/governance/ the governance-as-code spine.

Hard rules

No imports from, or runtime coupling to, any sibling fleet repository (self-contained). Third-party PyPI libraries are allowed under license and supply-chain review, kept minimal, and excluded from the execution core; the runtime deps are pydantic (boundary validation) and the optional psycopg (ADR-0014).
The nine invariants in CLAUDE.md are load-bearing. Each has a test.
Governance traceability: decisions are ADRs, work is BL-NNN, safety and security requirements are STPA-derived.
make check (ruff + mypy strict + pytest) plus the schema and eval gates must pass before a change is real.
Never weaken a default to make something pass.
Treat all collected host data, command output, and external feeds as untrusted (SEC-4); keep read tools and act tools separable; keep the human gate between observation and actuation (DRY_RUN, then approval, then execute; invariants 6, 8).
Never log command output bodies: the audit stores output_sha256 + output_len only, redaction covers secrets, and the logger never raises (invariant 3).

Read the full file on GitHub · 52 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.

2mo ago First seen · 52 lines · 677 tokens per session scan A f9e0c2b6b1ee

Subscribe to this mod's changes

aiops-mcp AGENTS.md is an instructions file published in the GitHub repository rmednitzer/aiops-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 677 tokens to every session, about $0.0027 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 2026-08-31.

DevOps and cloud aiops drift-detection fleet-management infrastructure mcp model-context-protocol

aiops-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
aiops-mcp AGENTS.mdrmednitzer/aiops-mcp	Instructions file	0	1mo ago	Apache-2.0	A	677	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

aiops-mcp: Instructions file for Codex