What is ai-automation-lab CLAUDE.md?

Project instructions for ai-automation-lab, an incident-triage service for a K3s home server cluster. It investigates alerts with read-only tools and stores results for comparison with confirmed causes.

Use them when developing or investigating the ai-automation-lab service, its alert workflow, database, or cluster-tool integrations.

They explain the project's purpose, technical stack, important files, and verification expectations before code changes are made.

How batpepe/ai-automation-lab configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to batpepe/ai-automation-lab. 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/batpepe/ai-automation-lab/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/batpepe/ai-automation-lab

Made for: Claude Code.

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/batpepe/ai-automation-lab/claude-md/github.svg)](https://agentmods.dev/instructions/batpepe/ai-automation-lab/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/batpepe/ai-automation-lab/claude-md"><img src="https://agentmods.dev/badge/instructions/batpepe/ai-automation-lab/claude-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/batpepe/ai-automation-lab/claude-md"><img src="https://agentmods.dev/badge/instructions/batpepe/ai-automation-lab/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,017 This file is loaded in full into every session.

When invoked 1,017 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	$0.01017	$0.01017
Opus 5.5	$0.00407	$0.00407
Sonnet 5.5	$0.00203	$0.00203
Haiku 4.5	$0.00102	$0.00102

Measured 2mo ago against content hash 93438021ae15, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-automation-lab 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 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.

CLAUDE.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Approach

Read files before writing. Don't re-read unchanged files.
Thorough in reasoning, concise in output.
No preamble, closing fluff, or sycophancy.
No emojis, em-dashes, or smart quotes in files or commits.
Verify SHAs, versions, flags, endpoints and API shapes by reading code or docs before asserting.
Targeted edits over rewrites.
Comments say why, not what. Every non-obvious config line carries its reason.

What this is

An incident triage agent for the K3s homelab described in the sibling repo devops-homelab-k3s-hybrid-cloud. Alertmanager fires, n8n dedupes and calls this service, the agent investigates with read-only cluster tools, and the result is persisted and later scored against the human-confirmed root cause. The measured accuracy is the point of the project, not the agent.

Stack

Key paths

plan.md phases, definitions of done, pushback on the brief
src/opsagent/config.py settings, OPSAGENT_ prefix, safe defaults
src/opsagent/observability/ logging now, metrics and probes in phase 5
src/opsagent/tools/ cluster tools, one registry, redacted outputs (phase 2)
src/opsagent/redaction/ the choke point every tool output passes through (phase 2)
src/opsagent/providers/ LLMProvider protocol, mock default, no paid keys (phase 3)
src/opsagent/agent/ loop, budget and depth caps, TriageReport (phase 3)
src/opsagent/n8n/ public API client and workflow export/import (phase 1)
workflows/ n8n workflow JSON, the source of truth for the instance
deploy/argocd/ child Applications; the platform repo points one app here
evals/scenarios/ fault injection scenarios and expected root causes (phase 6)
docs/adr/ decisions and the alternatives rejected

Read the full file on GitHub · 70 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 · 70 lines · 1,017 tokens per session scan A 93438021ae15

Subscribe to this mod's changes

ai-automation-lab CLAUDE.md is an instructions file published in the GitHub repository batpepe/ai-automation-lab (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,017 tokens to every session, about $0.0041 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.

ai-automation-lab CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-automation-lab CLAUDE.mdbatpepe/ai-automation-lab	Instructions file	0	2mo ago	MIT	A	1,017	Claude Code
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

ai-automation-lab: Instructions file for Claude Code