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/dev_workflowgit 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 | $0.02459 | $0.02459 |
| Opus 5 | $0.01229 | $0.01229 |
| Sonnet 5 | $0.00492 | $0.00492 |
| Haiku 4.5 | $0.00246 | $0.00246 |
Grade A, and why
dev_workflow 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.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Development Workflow
This document outlines the standard, iterative process for all development work. Following this workflow is mandatory to ensure consistency, quality, and effective collaboration across the project.
The Core Development Loop
All work, from new features to bug fixes, follows this fundamental three-phase cycle:
REMEMBER: This repository uses main as the default branch. NEVER commit directly to main!
-
Phase 1: Planning & Alignment
- Select an issue from the backlog.
- Switch to the
mainbranch and pull the latest changes. - Create a dedicated feature branch from
main(NEVER work directly onmain). - Explore the codebase to create a detailed implementation strategy.
-
Phase 2: Iterative Implementation
- Log your plan first. Document your intended changes in the relevant issue before writing code.
- Implement the changes, adhering to the project's architectural guidelines.
- Continuously log progress, discoveries, and setbacks as you work to create a rich history of the task.
-
Phase 3: Finalization & Committing
- Write and pass all required tests.
- Format your code according to project standards.
- Update any relevant project rules based on your changes.
- Commit your work using a structured, conventional commit message.
- Push your branch and create a PR.
Phase 1: Planning & Alignment
Before writing a single line of implementation code, you must have a clear plan and be working on the correct branch.
1.1. Select an Issue & State Your Intent
- List Open Issues: Use
mcp_github_list_issuesto see available tasks forgiantswarm/mcp-debug. - Choose an Issue: Select the highest-priority issue you are able to work on.
- Get Details: Use
mcp_github_get_issueto retrieve its full details. - Announce Your Plan: In the chat, you MUST summarize the issue (title, number) and your intended high-level approach.
- Example: "I am starting work on issue #37: Refactor Capability API. My plan is to start by defining the new interfaces in the API package..."
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 · 256 lines · 2,459 tokens per session scan A bb39872f3515
dev_workflow is a cursor rule published in the GitHub repository giantswarm/mcp-debug (37 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,459 tokens to every session, about $0.0123 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…