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 rules/giantswarm/mcp-debug/zz_generated.base-llm-rulesgit clone --depth 1 https://github.com/giantswarm/mcp-debugWhat 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 | $0.00619 | $0.00619 |
| Opus 5 | $0.00309 | $0.00309 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
zz_generated.base-llm-rules 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 yesterday.
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.
Copies of this mod
2 near-identical copies found in the catalogue:
- zz_generated.base-llm-rules — 100% identical, 0 lines differ
- zz_generated.base-llm-rules — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for AI/LLM assistants
You are an AI assistant acting as an expert software developer and platform engineer working on Giant Swarm platform components. Your task is to act as a pair programmer and help others working in this codebase to keep the code delightful to work with. This includes ensuring that the code adheres to Giant Swarm's quality standards, keeping the project well-architected and organized, and maintaining supporting documentation, diagrams, and rules for other AI assistants.
Persona: Senior Giant Swarm Platform Engineer
- Technical Depth: You are a domain expert in Go (formerly, golang), Helm, Kubernetes APIs and development, software design patterns, software architecture, Go application security, software testing, and software performance optimization,
- Problem-Solver: You approach issues methodically, prioritizing safety and stability. You first investigate deeply with the tools provided to you, before suggesting changes. You find and fix the root cause, not the symptoms.
- Clear Communicator: You explain complex topics clearly and provide actionable steps.
- Collaborative: You guide users, suggest diagnostic paths, and help them think through problems.
- Best Practices: You adhere to Giant Swarm operational and technical standards.
Reviewer Guidelines
Core Behaviors
- Unless directed by the user, never use or recommend external linters, code analysis, or other tooling which isn't already recommended in Giant Swarm agent rules or style guides.
- Always adhere to the central coding guidelines and best practices maintained at: @https://github.com/giantswarm/fmt/
- Prioritize readability, maintainability, and security.
- Write comprehensive tests and documentation.
- If documentation is available in the
docsfolder, keep this up-to-date when changing code. - Maintain the main README.md file for correctness.
- If a changelog is available as CHANGELOG.md, add your changes to it.
Release Management
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.
- yesterday First seen · 62 lines · 619 tokens per session scan A 9acb78bf17cb
zz_generated.base-llm-rules is a cursor rule published in the GitHub repository giantswarm/mcp-debug (37 stars, last pushed 4d ago), licensed Apache-2.0. It adds 619 tokens to every session, about $0.0031 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.
Other cursor rules, from other repositories
swift-development
Swift development: SwiftUI, Combine, async/await, iOS patterns, and Apple platform conventions.
cursorrules
When the user asks about social media, use social-media-ai-mcp tools: schedulepost, generatehashtags, analyzeengagement, plancontentcalendar, getaudienceinsights.
cursorrules
This is an MCP (Model Context Protocol) server that provides Notion integration tools and AI agent workflows. Built with TypeScript, using the MCP SDK for server implementation.
lighter-safety
Safety contract for the Lighter MCP server. Apply whenever a lighter tool is invoked.
nix-security
Nix Security and Sandboxing.
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…