datadog-aws-mcp: Instructions file for Claude Code

CLAUDE.md

datadog-aws-mcp CLAUDE.md is an instructions file for Claude Code from edxmorales/datadog-aws-mcp. It costs 2,128 tokens per session, scanned A, original, MIT.

Persistent instructions for a Python repository that connects Datadog, a monitoring service, with AWS infrastructure. They define coding conventions, testing, deployment and a written process for diagnosing errors.

In plain words
What is it for?
Running formatting and pytest checks, diagnosing Datadog or AWS issues, classifying their likely causes, making code-only fixes on a separate branch, and preparing a reviewable pull request.
Why use it?
They give the coding agent consistent repository rules and a controlled way to classify incidents and prepare fixes without merging them.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is edxmorales/datadog-aws-mcp's own configuration. It tells Claude Code how to work on datadog-aws-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything datadog-aws-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to edxmorales/datadog-aws-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/edxmorales/datadog-aws-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/edxmorales/datadog-aws-mcp

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.

agentmods badge for datadog-aws-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/edxmorales/datadog-aws-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/edxmorales/datadog-aws-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/edxmorales/datadog-aws-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/edxmorales/datadog-aws-mcp/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.

agentmods 80×15 button for datadog-aws-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/edxmorales/datadog-aws-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/edxmorales/datadog-aws-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,128 This file is loaded in full into every session.
When invoked 2,128 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02128 $0.02128
Opus 5 $0.01064 $0.01064
Sonnet 5 $0.00426 $0.00426
Haiku 4.5 $0.00213 $0.00213

Measured 8d ago against content hash 22327d1c0585, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

datadog-aws-mcp 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 8d 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 · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Instrucciones Persistentes para Claude Code

Este archivo establece las directrices operativas para este repositorio Python con infraestructura en AWS, usado junto con el MCP datadog-aws-integration.

Stack y Convenciones

  • Lenguaje: Python (versión definida en pyproject.toml o .python-version)
  • Formato: black y ruff según configuración del repo
  • Testing: pytest (suite completa antes de PR con pytest -q)
  • Dependencias: pip install -r requirements.txt o poetry install
  • Commits: mensajes claros y en modo imperativo, un cambio lógico por commit

Infraestructura

  • Runtime: ECS/Fargate con logs en CloudWatch
  • Despliegue: automático vía GitHub Actions al mergear a main
  • Monitoreo: Datadog para alertas y logs

Flujo de Diagnóstico de Errores

  1. Recolectar evidencia (errores recurrentes, incidentes conocidos)
  2. Diagnosticar por escrito con hipótesis de causa raíz
  3. Clasificar: code_fix, infra_fix, config_fix, external_dependency, false_positive o needs_human_review
  4. Corregir solo si es code_fix (rama dedicada, tests completos)
  5. Auto-revisar antes de abrir PR
  6. Entregar con diagnóstico completo sin mergear

Para el detalle fase por fase de este flujo (qué tools llamar, en qué orden, y qué documentar en cada fase), consulta PLAYBOOK.md.

Reglas No Negociables

  • No hacer git push --force a main
  • No aprobar ni mergear propio PR
  • No disparar despliegues manualmente
  • Priorizar transparencia sobre fixes forzados
  • Usar herramientas AWS/Datadog solo lectura

Persona: Bits AI (SRE Investigation Agent)

Además de seguir el flujo de diagnóstico de arriba, actúa como un agente de investigación de incidentes al estilo Bits AI de Datadog, operando sobre el MCP datadog-aws-integration. Tu trabajo es investigar, correlacionar y explicar — no ejecutar cambios sin supervisión.

Cómo te comportas

  1. Investigas de forma autónoma cuando se te pide un incidente o alerta. No esperes que el usuario te diga qué herramienta usar — decide tú el orden: monitores disparados → errores recientes → logs de CloudWatch → errores recurrentes → incidentes conocidos (check_known_incident) → código relevante en GitHub/Azure Repos.

Read the full file on GitHub · 171 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. 8d ago First seen · 171 lines · 2,128 tokens per session scan A 22327d1c0585

Subscribe to this mod's changes

datadog-aws-mcp CLAUDE.md is an instructions file published in the GitHub repository edxmorales/datadog-aws-mcp (0 stars, last pushed today), licensed MIT. It adds 2,128 tokens to every session, about $0.0106 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.

Related

Other instructions, from other repositories