cursorrules

Project-specific development rules for a Python 3.11+ backend that uses LangGraph, LangChain, and the A2A protocol. It also documents testing, package management, Docker Compose, and commit conventions.

In plain words
What is it for?
Use it when adding or reviewing backend code, running tests with pytest, managing packages with uv, changing Docker Compose setup, or preparing Git commits.
Why use it?
It gives an AI coding assistant the repository’s expected tools and working practices, reducing inconsistent changes and incorrect setup instructions.

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/caipe-io/ai-platform-engineering/cursorrules
Clone the repo
git clone --depth 1 https://github.com/caipe-io/ai-platform-engineering

Made for: Cursor.

Per session 3,624 This file is loaded in full into every session.
When invoked 3,624 The same file — it is already loaded in full.
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 $0.03624 $0.03624
Opus 5 $0.01812 $0.01812
Sonnet 5 $0.00725 $0.00725
Haiku 4.5 $0.00362 $0.00362

Measured 2d ago against content hash 7ef9be122c25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 2d 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.

.cursorrules · 588 lines

How it starts

The opening of the file, as written. The whole thing — 588 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Platform Engineering Development Rules

Repository Information

Project: AI Platform Engineering Type: Python Backend for AI Agents & Multi-Agent System Language: Python 3.11+ Framework: LangGraph, LangChain, A2A Protocol Package Manager: uv Testing: pytest

Docker Compose First Install

When changing docker-compose.yaml, docker-compose.dev.yaml, .env.example, release image tags, Compose profiles, Keycloak/OpenFGA/RAG defaults, or first-launch UX, follow .claude/skills/docker-compose-first-install/SKILL.md. The plain OSS path must work from .env.example with:

mcp-servers,caipe-ui-prod,rbac,caipe-supervisor,dynamic-agents,rag,caipe-mongodb,web_ingestor

Do not add Slack/Webex bots to that default all-in-one path.

Git Commit Standards

Conventional Commits (REQUIRED)

All commits MUST follow the Conventional Commits specification:

<type>[optional scope]: <description>

[optional body]

[optional footer(s)]
Commit Types
  • feat: A new feature

    feat: add ArgoCD MCP pagination support
    feat(supervisor): implement TODO-based execution plan
    feat(agent): add OOM protection for large queries
    
  • fix: A bug fix

    fix: resolve A2A artifact streaming race condition
    fix(argocd): handle 819 applications without OOM
    fix(streaming): prevent duplicate artifact warnings
    
  • docs: Documentation only changes

    docs: add ADR for OOM protection strategy
    docs(adr): document MCP pagination implementation
    
  • perf: Performance improvements

    perf(argocd): optimize pagination for large datasets
    perf(mcp): reduce memory usage in list operations
    
  • refactor: Code change that neither fixes a bug nor adds a feature

    refactor(agent): simplify context window management
    
  • test: Adding missing tests or correcting existing tests

    test: add integration tests for pagination
    
  • build: Changes to build system or dependencies

    build: update langchain to v0.2.0
    build(docker): optimize multi-agent containers
    

Read the full file on GitHub · 588 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. 2d ago First seen · 588 lines · 3,624 tokens per session scan A 7ef9be122c25

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository caipe-io/ai-platform-engineering (403 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,624 tokens to every session, about $0.0181 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 2026-08-30.