agentmods.dev

TheNightOps CLAUDE.md

TheNightOps CLAUDE.md is an instructions file for coding agents from nomadicmehul/TheNightOps. It costs 1,972 tokens per session, scanned A, original, Apache-2.0.

A set of Claude Code instructions describing the NightOps project, its software structure, its agents, and its connected tool servers.

In plain words
What is it for?
Use it when developing or maintaining NightOps, an operations agent for investigating and responding to Kubernetes incidents with Google ADK, Gemini, and MCP servers.
Why use it?
It gives Claude Code project-specific context so it can work with the codebase and its Kubernetes operations more consistently.

Instructions file

not rated 1 2mo ago A scan 1,972 tokens original Apache-2.0
View the source file nomadicmehul/TheNightOps
Install

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.

agentmods
npx agentmods add instructions/nomadicmehul/thenightops/claude-md
Clone the repo
git clone --depth 1 https://github.com/nomadicmehul/TheNightOps

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 TheNightOps CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nomadicmehul/thenightops/claude-md.svg)](https://agentmods.dev/instructions/nomadicmehul/thenightops/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nomadicmehul/thenightops/claude-md"><img src="https://agentmods.dev/badge/instructions/nomadicmehul/thenightops/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,972 This file is loaded in full into every session.
When invoked 1,972 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01972 $0.01972
Opus 5 $0.00986 $0.00986
Sonnet 5 $0.00394 $0.00394
Haiku 4.5 $0.00197 $0.00197

Measured 4d ago against content hash c1992cd8d3b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

TheNightOps CLAUDE.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 4d 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.

CLAUDE.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions

Project Overview

THE NightOps (Triage. Heal. Evolve.) — Autonomous SRE Agent for Kubernetes, built on Google ADK and Gemini.

  • Version: 0.1.0b1
  • License: Apache 2.0
  • Python: 3.11+
  • Package manager: pip with hatchling build backend
  • CLI entry point: nightops (mapped to nightops.cli:app)

Architecture

Multi-agent system using Google ADK for orchestration and MCP (Model Context Protocol) for tool integration.

Agent Layer (ADK + Gemini)

  • Root Orchestrator (src/agents/root_orchestrator.py) — Coordinates investigation across sub-agents
  • Log Analyst (src/agents/log_analyst.py) — Cloud Logging pattern analysis
  • Deployment Correlator (src/agents/deployment_correlator.py) — K8s events, pod health, recent deployments
  • Runbook Retriever (src/agents/runbook_retriever.py) — Grafana alerts, dashboards, past incidents
  • Communication Drafter (src/agents/communication_drafter.py) — RCA generation, Slack/email/Telegram notifications
  • Anomaly Detector (src/agents/anomaly_detector.py) — Proactive anomaly detection

MCP Servers

Official Google Cloud MCP (default for GCP/demo):

  • GKE MCP — https://container.googleapis.com/mcp (IAM auth via header_provider)
  • Cloud Observability MCP — https://logging.googleapis.com/mcp (IAM auth via header_provider)

Custom MCP Servers (for --local mode):

  • Kubernetes (src/mcp_servers/kubernetes/server.py) — Pod status, events, deployments, logs
  • Cloud Logging (src/mcp_servers/cloud_logging/server.py) — GCP log queries
  • Slack (src/mcp_servers/slack/server.py) — Incident notifications (disabled)
  • Notifications (src/mcp_servers/notifications/server.py) — Email/Telegram/WhatsApp (disabled)

Core Modules

  • Config (src/core/config.py) — Pydantic settings, loads from config/.env and config/nightops.yaml
  • Models (src/core/models.py) — WebhookAlert, RemediationAction, IncidentRecord, AnomalyCheck, compute_fingerprint
  • Autodiscovery (src/core/autodiscovery.py) — Environment auto-detection
  • CLI (src/cli.py) — Typer-based CLI with commands: agent, verify, metrics, policies, auto-config, demo, dashboard, mcp, init

Read the full file on GitHub · 177 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. 4d ago First seen · 177 lines · 1,972 tokens per session scan A c1992cd8d3b2

Subscribe to this mod's changes

TheNightOps CLAUDE.md is an instructions file published in the GitHub repository nomadicmehul/TheNightOps (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,972 tokens to every session, about $0.0099 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 2026-08-31.

Building agentsadk-googleadk-pythonai-agentsaiopsaiops-agent
Related

Other instructions, from other repositories

lmnr CLAUDE.md

Claude Code instructions for lmnr-ai/lmnr, covering claude.md, project overview, repository structure, development commands and frontend (next.js).

lmnr-ai/lmnr · 2,360 tokens

openinference AGENTS.md

Instructions for Arize-ai/openinference, covering claude.md, repository overview, repository structure, essential commands by language and python.

Arize-ai/openinference · 1,064 tokens

aura CLAUDE.md

Claude Code instructions for mezmo/aura, covering claude.md - project documentation, current status: production ready, quick start, build and start web server (default config.toml).

mezmo/aura · 5,043 tokens

siclaw AGENTS.md

Instructions for scitix/siclaw, covering siclaw project instructions, project shape, before risky edits, verification and stable boundaries.

scitix/siclaw · 829 tokens

aurora AGENTS.md

AGENTS.md instructions for Arvo-AI/aurora, covering aurora - agent guidelines, commands, docker deployments, architecture and secrets management (vault).

Arvo-AI/aurora · 2,731 tokens

ongrid AGENTS.md

AGENTS.md instructions for ongridio/ongrid, covering agents.md, agent 必读, 第一步：找到 gospec 任务路由表, 第二步：路由 → 加载 and 第三步：实施 + 自查.

ongridio/ongrid · 1,980 tokens