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.
npx agentmods add instructions/amartinawi/eks_dubugger/agents-mdgit clone --depth 1 https://github.com/amartinawi/EKS_DubuggerWrote 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.
[](https://agentmods.dev/instructions/amartinawi/eks_dubugger/agents-md)<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>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 | $0.11618 | $0.11618 |
| Opus 5 | $0.05809 | $0.05809 |
| Sonnet 5 | $0.02324 | $0.02324 |
| Haiku 4.5 | $0.01162 | $0.01162 |
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) 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)
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.
- 5d ago First seen · 1,152 lines · 11,618 tokens per session scan A c512f94d97e5
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.
Other instructions, from other repositories
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
agent-skills fortrabbit.instructions.md
Instructions for fortrabbit/agent-skills, covering fortrabbit — github copilot instructions, what fortrabbit is, configuration lookup, available operations and mcp server (optional).
cron-mcp CLAUDE.md
Claude Code instructions for Shreyas-Profile/cron-mcp, covering deploying cron-mcp to hetzner + regiq.in, server (shared with the rest of the globalion mcp fleet), deploy a new version, first-time subdomain wiring (cron.regiq.in) and env vars.
Railway-mcp CLAUDE.md
Claude Code instructions for Travis-Gilbert/Railway-mcp, covering railway mcp server, quick reference, file map, architecture and key patterns.
equinix-fabric-mcp CLAUDE.md
Claude Code instructions for sliuuu/equinix-fabric-mcp, covering claude.md — equinix-fabric-mcp, canonical files, auth, add equinixclientid and equinixclientsecret and running.