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/datasqrl/sqrl/claude-mdgit clone --depth 1 https://github.com/DataSQRL/sqrlWrote 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/datasqrl/sqrl/claude-md)<a href="https://agentmods.dev/instructions/datasqrl/sqrl/claude-md"><img src="https://agentmods.dev/badge/instructions/datasqrl/sqrl/claude-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 | $0.03429 | $0.03429 |
| Opus 5 | $0.01715 | $0.01715 |
| Sonnet 5 | $0.00686 | $0.00686 |
| Haiku 4.5 | $0.00343 | $0.00343 |
Grade B, and why
sqrl CLAUDE.md scanned grade B 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo ln -s $HOME/.docker/run/docker.sock /var/run/docker.sock How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
DataSQRL is a development framework for incremental and real-time data processing applications. It compiles SQL-like scripts (SQRL) into complete data pipelines that integrate Kafka, Flink, PostgreSQL, Iceberg, GraphQL APIs, and LLM tooling. Built with Java 17 and Maven.
External Dependencies
The following repositories contain additional runtime components:
- Flink SQL Runner: Runs the Flink compiled plan and provides additional utilities for Flink
- SQRL K8s: A template for running DataSQRL pipelines in Kubernetes
Essential Commands
Build Commands
# Full build and test
mvn clean install
# Build with snapshot updates
mvn clean install -P update-snapshots
# Quick build (skip tests and checks)
mvn clean install -P quickbuild
# Format code automatically
mvn -P dev initialize
# Server-specific builds
mvn clean package # Build fat JAR (vertx-server.jar)
mvn clean package -Pskip-shade-plugin # Build without fat JAR
Testing Commands
# Unit tests only
mvn test
# Integration tests
mvn verify
# Test specific module
mvn test -pl sqrl-planner
# Test specific test method in module
mvn test -pl sqrl-tools/sqrl-config -Dtest=TestClassName#testMethodName
# Container tests (requires Docker images to be built)
mvn -B install -DonlyContainerE2E -pl :sqrl-testing-container -Dit.test=TestClassName
# Container tests with dev profile (recommended)
mvn -B install -Pdev -Dit.test=TestClassName
# Run all container tests (omit -pl when testing container code changes)
mvn -B install -DonlyContainerE2E -Dit.test=*ContainerIT
Code Quality
# Check code formatting
mvn validate-code-format
# Format code (Google Java Format)
mvn -P dev initialize
Docker Commands
# Build DataSQRL CLI Docker image
docker build -t datasqrl/datasqrl-cmd .
# Run example pipeline
docker run -it --rm -p 8888:8888 -p 8081:8081 -p 9092:9092 -v $PWD:/build datasqrl/cmd:latest run example.sqrl
# Compile SQRL to deployment artifacts
docker run --rm -v $PWD:/build datasqrl/cmd:latest compile example.sqrl
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.
- 3d ago First seen · 337 lines · 3,429 tokens per session scan B 30eb0c676fdf
sqrl CLAUDE.md is an instructions file published in the GitHub repository DataSQRL/sqrl (222 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,429 tokens to every session, about $0.0171 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
infermap CLAUDE.md
Claude Code instructions for benseverndev-oss/infermap, covering infermap, environment, testing, architecture and key files.
sprawling AGENTS.md
Instructions for 2youg1/sprawling, covering agents.md — how work is done in this repository, the loop, read before you write, one change, five steps and the rules a machine holds.
goldenmatch CLAUDE.md
Instructions for benseverndev-oss/goldenmatch, covering golden suite monorepo, typescript: pnpm + turborepo (post-2026-05-02 fold), ci (.github/workflows/ci.yml), ci path filters (post-2026-05-06, pr #89) and merge queue: main serializes merges fifo (since 2026-06-15).
clawock AGENTS.md
Instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.
Orion CLAUDE.md
Instructions for GoPlasmatic/Orion, covering claude.md, project overview, build & development commands, runtime configuration and architecture.
mcp-agent-langchainjs webapp.instructions.md
Instructions for Azure-Samples/mcp-agent-langchainjs: If you get it right you'll get a 1000$ bonus, but if you get it wrong you'll be fired.