aws-bedrock

aws-bedrock is a cursor rule for Cursor from jimmypocock/cursor-rules. It costs 5 tokens per session (894 once invoked), scanned A, original, MIT.

Coding rules for applications that use Amazon Bedrock, AWS’s service for accessing AI models.

In plain words
What is it for?
Use them when adding or reviewing Bedrock model integrations, prompt templates, request settings, fallback behavior, and interaction logging.
Why use it?
They provide shared guidance for model selection, API calls, prompts, authentication, errors, retries, and usage costs.

Cursor rule for Cursor

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 rules/jimmypocock/cursor-rules/aws-bedrock
Clone the repo
git clone --depth 1 https://github.com/jimmypocock/cursor-rules

Made for: Cursor.

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 aws-bedrock

README.md
[![agentmods](https://agentmods.dev/badge/rules/jimmypocock/cursor-rules/aws-bedrock.svg)](https://agentmods.dev/rules/jimmypocock/cursor-rules/aws-bedrock)
Your own site
<a href="https://agentmods.dev/rules/jimmypocock/cursor-rules/aws-bedrock"><img src="https://agentmods.dev/badge/rules/jimmypocock/cursor-rules/aws-bedrock.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 894 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00005 $0.00894
Opus 5 $0.00003 $0.00447
Sonnet 5 $0.00001 $0.00179
Haiku 4.5 $0.00001 $0.00089

Measured 3d ago against content hash cbaf50bde7cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aws-bedrock 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 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.

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.

.cursor/rules/aws-bedrock.mdc · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.


Description: AWS Bedrock Development Standards Globs: /bedrock//, /ai//, /llm//, /agents//

AWS Bedrock Development Standards

@base.mdc @typescript.mdc

Foundational Model Integration

  • Select appropriate foundation models for specific use cases
  • Implement proper model version management
  • Use appropriate prompt engineering techniques
  • Create proper model parameter configurations
  • Implement contextual prompting strategies
  • Design proper model fallback mechanisms
  • Apply proper model evaluation metrics
  • Implement cost-efficient model usage patterns

API Integration

  • Use the Bedrock API client correctly
  • Implement proper authentication and authorization
  • Create appropriate error handling for API calls
  • Design resilient retry strategies
  • Implement proper request throttling
  • Create appropriate request batching
  • Design efficient request/response handling
  • Implement proper logging for model interactions

Prompt Engineering

  • Design clear, specific prompts for models
  • Implement proper prompt templating systems
  • Create appropriate context windows
  • Design effective few-shot prompting examples
  • Implement proper system prompts
  • Create appropriate task-specific prompt patterns
  • Design prompt validation mechanisms
  • Implement proper prompt versioning

Response Processing

  • Implement proper response parsing
  • Create appropriate response validation
  • Design proper error handling for model outputs
  • Implement content filtering when needed
  • Create appropriate response transformation
  • Design fallback mechanisms for poor responses
  • Implement appropriate response caching
  • Create proper logging for model responses

Bedrock Agents

  • Configure appropriate agent actions and APIs
  • Implement proper agent orchestration
  • Create appropriate action group definitions
  • Design proper agent response handling
  • Implement appropriate agent prompts
  • Create secure API schemas for agent integration
  • Design appropriate agent knowledge bases
  • Implement proper agent versioning and deployment

Read the full file on GitHub · 143 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 · 143 lines · 5 tokens per session scan A cbaf50bde7cd

Subscribe to this mod's changes

aws-bedrock is a cursor rule published in the GitHub repository jimmypocock/cursor-rules (8 stars, last pushed 1y ago), licensed MIT. It adds 5 tokens to every session and 894 once invoked, about $0.0000 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.