Borrowing it
Nothing to install: this file belongs to HatmanStack/RAGStack-Lambda. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HatmanStack/RAGStack-Lambda/main/CLAUDE.mdgit clone --depth 1 https://github.com/HatmanStack/RAGStack-LambdaWrote 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/hatmanstack/ragstack-lambda/claude-md)<a href="https://agentmods.dev/instructions/hatmanstack/ragstack-lambda/claude-md"><img src="https://agentmods.dev/badge/instructions/hatmanstack/ragstack-lambda/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.
<a href="https://agentmods.dev/instructions/hatmanstack/ragstack-lambda/claude-md"><img src="https://agentmods.dev/badge/instructions/hatmanstack/ragstack-lambda/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01549 | $0.01549 |
| Opus 5.5 | $0.00620 | $0.00620 |
| Sonnet 5.5 | $0.00310 | $0.00310 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
RAGStack-Lambda 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working with this repository.
READ FIRST - Problem Solving Discipline
Never fix a symptom without investigating what else shares that pattern.
Before declaring any fix complete:
- Trace the full flow - If a GraphQL field is missing, diff the entire query against the entire schema
- Check related systems - If CSP blocks one resource type, check all resource types the component uses
- Question existence - If a file causes problems, ask whether it should exist at all
- Follow the data - Trace from UI → GraphQL → resolver → Lambda → S3/DynamoDB and back
When you encounter an error, your first action is investigation, not a fix.
Project Overview
RAGStack-Lambda is a serverless document processing pipeline with AI chat on AWS. Documents are uploaded → OCR processed (Textract/Bedrock) → vectorized → stored in Bedrock Knowledge Base → queryable via chat interface.
Single SAM stack: Document processing pipeline (Lambda, Step Functions, S3, DynamoDB, Bedrock KB), Chat API (AppSync GraphQL, Cognito auth), <ragstack-chat> web component (CloudFront CDN)
Prerequisites
- Python 3.13+ (use
uvfor all Python package management) - Node.js 24+
- AWS CLI, SAM CLI (configured)
- Docker (required for Lambda layer builds)
Common Commands
# Testing
npm run test # All tests (backend + frontend)
npm run test:backend # Python tests (pytest -n auto)
npm run test:frontend # UI + ragstack-chat tests (vitest)
npm run test:integration # Integration tests (requires deployed stack)
uv run pytest tests/unit/python/test_config.py -v # Single test file
# Linting
npm run lint # Python (ruff check + format --check)
npm run lint:fix # Python autofix
npm run lint:frontend # TypeScript (ESLint --max-warnings 0)
npm run check # Lint + test (CI equivalent)
# Deployment (defaults to us-east-1 for Nova Multimodal Embeddings)
python publish.py --stack-name my-docs --admin-email [email protected]
python publish.py --stack-name my-docs --admin-email [email protected] --skip-ui # Skip dashboard
python publish.py --stack-name my-docs --admin-email [email protected] --skip-ui-all # Skip all UI
python publish.py --stack-name my-docs --admin-email [email protected] --demo-mode # Enable demo mode
# Development
sam build
sam local invoke ProcessDocumentFunction --event tests/events/sqs-processing-message.json
cd src/ui && npm run dev # Frontend dev server
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.
- 2mo ago First seen · 126 lines · 1,549 tokens per session scan A fbeecdf064aa
RAGStack-Lambda CLAUDE.md is an instructions file published in the GitHub repository HatmanStack/RAGStack-Lambda (25 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,549 tokens to every session, about $0.0062 per session on Opus 5.5. 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.