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.
git clone --depth 1 https://github.com/giantswarm/mcp-debugWrote 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/rules/giantswarm/mcp-debug/architecture)<a href="https://agentmods.dev/rules/giantswarm/mcp-debug/architecture"><img src="https://agentmods.dev/badge/rules/giantswarm/mcp-debug/architecture/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/rules/giantswarm/mcp-debug/architecture"><img src="https://agentmods.dev/badge/rules/giantswarm/mcp-debug/architecture.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 | $0.00333 | $0.00333 |
| Opus 5.5 | $0.00133 | $0.00133 |
| Sonnet 5.5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
architecture 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- architecture — 92% identical, 4 lines differ
What it actually says
Architecture Principles
This document outlines the fundamental architectural principles and patterns for the mcp-debug codebase. Adherence to these guidelines is mandatory to maintain a clean, decoupled, and testable system.
1. Testing Standards
- Minimum Coverage: All new code MUST achieve at least 80% unit test coverage.
- No Flaky Tests: Tests MUST be deterministic. Do not use
time.Sleepor other mechanisms that can lead to race conditions. Use dependency injection for things like clocks or timers to make code testable.
2. Go Development & Style
- Formatting: Before every commit, run:
goimports -w . go fmt ./... - Dependencies: Before adding a new dependency with
go get, search the web to find its latest stable version. This is a must! - Error Handling: Wrap errors with
fmt.Errorf("context: %w", err)to preserve context. - File Size: Keep files focused and under 500 lines. Refactor larger files.
3. Documentation
- Packages: Every package MUST have a
doc.gofile explaining its purpose. - Exported Members: Every exported function, type, and variable MUST have a GoDoc comment.
- Project Docs: New features or significant changes require updates to the relevant documents in the
docs/directory.
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.
- 1mo ago First seen · 37 lines · 333 tokens per session scan A 78621394bccc
architecture is a cursor rule published in the GitHub repository giantswarm/mcp-debug (37 stars, last pushed today), licensed Apache-2.0. It adds 333 tokens to every session, about $0.0013 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 cursor rules, from other repositories
rails-cursorrules-prompt-file
Cursor rules for Rails development with basic setup.
testing
Vitest toolchain and testing discipline - two runtimes, no watch for agents, authoring gate, junk patterns.
testing-standards
Testing standards for pytest, fixtures, async patterns, and test organization. Apply when writing or reviewing tests.
api
For creating tests for the backend in bubblelab-api.
write-tests
Patterns for writing backend tests — integration tests with TestDB, unit tests for pure logic, test data seeding.
issues-tests
Backend test conventions — QuarkusTest, REST Assured, Given, ArchUnit.