EKS_Dubugger AGENTS.md

EKS_Dubugger AGENTS.md is an instructions file for Codex, OpenCode from amartinawi/EKS_Dubugger. It costs 11,618 tokens per session, scanned A, original, MIT.

A project guide for an Amazon EKS troubleshooting tool that examines Kubernetes clusters and creates HTML and machine-readable reports.

In plain words
What is it for?
Use it when running or changing checks for pod evictions, node problems, out-of-memory kills, CloudWatch metrics, or control-plane logs.
Why use it?
It gives coding agents the project structure, setup commands, analysis options, tests, and supported diagnostic areas.

Instructions file for CodexOpenCode

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

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/amartinawi/eks_dubugger/agents-md
Clone the repo
git clone --depth 1 https://github.com/amartinawi/EKS_Dubugger

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 EKS_Dubugger AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/amartinawi/eks_dubugger/agents-md.svg)](https://agentmods.dev/instructions/amartinawi/eks_dubugger/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/amartinawi/eks_dubugger/agents-md"><img src="https://agentmods.dev/badge/instructions/amartinawi/eks_dubugger/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 11,618 This file is loaded in full into every session.
When invoked 11,618 The same file — it is already loaded in full.
Security scan A 1 finding. 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 5.1 $0.11618 $0.11618
Opus 5 $0.05809 $0.05809
Sonnet 5 $0.02324 $0.02324
Haiku 4.5 $0.01162 $0.01162

Measured 5d ago against content hash c512f94d97e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

EKS_Dubugger AGENTS.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- subprocess → `subprocess.CalledProcessError`, `TimeoutExpired` (kubectl failures)
AGENTS.md · 1,152 lines

How it starts

The opening of the file, as written. The whole thing — 1,152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidelines for AI coding agents working in the EKS Health Check Dashboard codebase.

Project Overview

Python-based diagnostic tool for Amazon EKS cluster troubleshooting. Single-file application (eks_comprehensive_debugger.py) that analyzes pod evictions, node conditions, OOM kills, CloudWatch metrics, control plane logs, and generates interactive HTML reports.

Version: 5.0.0
Lines of Code: ~22,800 (debugger) + ~1,400 (MCP server)
Analysis Methods: 84
Correlation Rules: 18
Remediation Patterns: 45+
Catalog Coverage: 100% (79 issues across 3 catalogs)
MCP Tools: 18 (AI-agent discoverable via Model Context Protocol)
Unit Tests: 384 tests (382 passing, 2 slow performance tests)

Quick Commands

# Setup
python3 -m venv venv && source venv/bin/activate && pip install -r requirements.txt

# Run analysis (generates HTML + LLM-JSON reports)
python eks_comprehensive_debugger.py --profile <profile> --region <region> --cluster-name <cluster> --days 2

# With custom kubectl context
python eks_comprehensive_debugger.py --profile <profile> --region <region> --cluster-name <cluster> --kube-context <context-name> --days 1

# Run MCP server (stdio transport — for Claude Desktop)
python eks_mcp_server.py

# Run MCP server with HTTP transport (for remote access)
python eks_mcp_server.py --transport streamable-http --port 8080

# Inspect MCP tools interactively (web UI)
npx @modelcontextprotocol/inspector python eks_mcp_server.py

# Run unit tests
python3 -m pytest tests/ -v

# Lint/type check (optional)
ruff check eks_comprehensive_debugger.py
mypy eks_comprehensive_debugger.py --ignore-missing-imports

File Structure

eks_comprehensive_debugger.py  # Main debugger (~22,800 lines, all-in-one)
eks_mcp_server.py              # MCP server — 18 tools for AI agents (Phase 2)
requirements.txt               # Python dependencies (includes test deps)
.gitignore                     # Git ignore rules
README.md                      # User documentation
AGENTS.md                      # This file
tests/                         # Unit tests (384 tests)
├── __init__.py
├── conftest.py                # Shared fixtures
├── test_severity_classification.py  # Severity logic tests
├── test_input_validation.py         # Security/shell injection tests
├── test_findings.py                 # Findings management tests
├── test_kubectl_execution.py        # Kubectl shell safety tests
├── test_api_cache.py                # APICache tests
├── test_incremental_cache.py        # IncrementalCache tests
├── test_performance_tracker.py      # PerformanceTracker tests
├── test_ssm_integration.py          # SSM node diagnostics tests (Phase 1)
├── test_node_os_parsers.py          # Node OS output parser tests (Phase 1)
├── test_node_selection.py           # Node priority selection tests (Phase 1)
└── test_mcp_server.py               # MCP server tool tests (Phase 2)
venv/                          # Virtual environment (gitignored)

Read the full file on GitHub · 1,152 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. 5d ago First seen · 1,152 lines · 11,618 tokens per session scan A c512f94d97e5

Subscribe to this mod's changes

EKS_Dubugger AGENTS.md is an instructions file published in the GitHub repository amartinawi/EKS_Dubugger (5 stars, last pushed 2mo ago), licensed MIT. It adds 11,618 tokens to every session, about $0.0581 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.