agentmods.dev

infrawise AGENTS.md

Repository instructions for Infrawise, a tool that gives coding assistants current information about AWS infrastructure such as database keys, API routes, queues, and serverless function triggers.

In plain words
What is it for?
Use them when developing or reviewing Infrawise features that read infrastructure context or detect problems such as incorrect queue settings, missing dead-letter handling, or mismatched resource definitions.
Why use it?
They define the product’s goal and checks for preventing infrastructure mistakes, so generated code can match the deployed resources without repeatedly copying details from the AWS console.

Instructions file for CodexOpenCode

20 4d ago C scan 9,567 tokens original MIT
View the source file Sidd27/infrawise
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/sidd27/infrawise/agents-md
Clone the repo
git clone --depth 1 https://github.com/Sidd27/infrawise

Made for: Codex, OpenCode.

Per session 9,567 This file is loaded in full into every session.
When invoked 9,567 The same file — it is already loaded in full.
Security scan C 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 $0.09567 $0.09567
Opus 5 $0.04784 $0.04784
Sonnet 5 $0.01913 $0.01913
Haiku 4.5 $0.00957 $0.00957

Measured 3d ago against content hash 9deebcc68632, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

infrawise AGENTS.md scanned grade C 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 3d 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- **NO source code changes for local emulators — period.** `src/` is written for real AWS only. LocalStack and Floci are both reached through a standard AWS profile the user adds to their global `~/.aws/config` + `~/.aws
AGENTS.md · 591 lines

How it starts

The opening of the file, as written. The whole thing — 591 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Infrawise — AI instructions

Project goal

Genesis pain: Developers had to copy-paste DynamoDB schemas, RDS table definitions, and Lambda trigger shapes from the AWS console into their AI coding assistant every single session. Manual, repetitive, breaks flow, and still produces wrong code because the pasted context is incomplete.

What Infrawise is: The canonical tool for infra-aware AI coding. When a developer thinks "how does my AI assistant know my DynamoDB schema without me pasting it?" — the answer should be Infrawise. The positioning goal is to own the "infra-aware AI coding" category the way Prettier owns formatting or Husky owns git hooks.

Two product pillars:

Context (developer experience) — AI coding assistants know your live infrastructure. Exact partition keys, sort keys, GSIs, Lambda trigger event shapes, queue DLQ coverage, API routes and their Lambda bindings. The developer never looks at the AWS console mid-coding again. Write correct code the first time because the AI already knows the schema.

Guard (mistake prevention) — Surface costly infra mistakes before they ship. Wrong SQS visibility timeout causing duplicate Lambda processing. Missing DLQ silently dropping failed messages. A Lambda scanning a DynamoDB table without a GSI. RDS queries on unindexed columns. These are expensive to discover in production. Infrawise warns at coding time, not incident time.

What it covers today:

  • AWS: DynamoDB, Lambda, SQS, SNS, SSM Parameter Store, Secrets Manager, EventBridge, RDS, API Gateway, S3, CloudWatch Logs, Cognito, Kinesis, MSK (clusters), ElastiCache, CloudFront, CloudWatch metrics (opt-in runtime signals)
  • Databases: PostgreSQL, MySQL, MongoDB
  • Messaging: Apache Kafka via kafkajs (TS/JS) and kafka-python/confluent-kafka (Python) — broker-agnostic (self-hosted, Confluent, Redpanda, or Amazon MSK). Producer/consumer-to-topic mapping is extracted from application code (AST scan, always-on, no config key) and surfaced as topic nodes via get_topic_details. Distinct from the Amazon MSK Lambda trigger (detected from the event-source ARN, with event shape event.records[topic][0].value).
  • IaC: Terraform, CDK, CloudFormation (local file parsing for drift detection, plus stack outputs / cross-stack exports)
  • Code scanning: TypeScript/JavaScript (ts-morph) and Python (bundled stdlib-ast scanner run via python3 subprocess, requires python3 on PATH) — auto-detected by file signal, no config. Python detection: boto3 clients and dynamodb.Table() resources, cursor.execute/SQLAlchemy text() SQL, pymongo collections, kafka-python/confluent-kafka

Read the full file on GitHub · 591 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. 3d ago First seen · 591 lines · 9,567 tokens per session scan C 9deebcc68632

Subscribe to this mod's changes

infrawise AGENTS.md is an instructions file published in the GitHub repository Sidd27/infrawise (20 stars, last pushed 4d ago), licensed MIT. It adds 9,567 tokens to every session, about $0.0478 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai-toolsawsclaude-codeinfrastructuremcp-tools
Related

Other instructions, from other repositories

ol-infrastructure AGENTS.md

Instructions for mitodl/ol-infrastructure, covering agent instructions for ol-infrastructure repository, quick start, environment setup (one-time), validate your changes and documentation index.

mitodl/ol-infrastructure · 2,163 tokens

openFunctions CLAUDE.md

Instructions for Tom-R-Main/openFunctions, covering openfunctions — ai assistant context, what this is, architecture, how to define a tool and persistence.

Tom-R-Main/openFunctions · 2,680 tokens

claude-aws-cost-saver CLAUDE.md

Instructions for prajapatimehul/claude-aws-cost-saver, covering aws cost optimization system, quick start, list all checks, view specific check and see required aws cli commands.

prajapatimehul/claude-aws-cost-saver · 5,241 tokens

claude-aws-cost-saver AGENTS.md

Instructions for prajapatimehul/claude-aws-cost-saver, covering aws cost saver for codex, purpose, codex setup (mcp only), register the aws api mcp server used by this project and verify it is available.

prajapatimehul/claude-aws-cost-saver · 557 tokens

infrastructure-mcp CLAUDE.md

Instructions for radumalica/infrastructure-mcp, covering claude.md, project status, what this project is, commands and architecture.

radumalica/infrastructure-mcp · 886 tokens

agenticTrader CLAUDE.md

Claude Code instructions for TerminatrX/agenticTrader, covering agentic-trader, safety rules — non-negotiable, architecture, the seam and layout.

TerminatrX/agenticTrader · 3,908 tokens