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/emmahyde/thinking-patterns/mcp-agent-rulesgit clone --depth 1 https://github.com/emmahyde/thinking-patternsWhat 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 | $0.02345 | $0.02345 |
| Opus 5 | $0.01172 | $0.01172 |
| Sonnet 5 | $0.00469 | $0.00469 |
| Haiku 4.5 | $0.00234 | $0.00234 |
Grade A, and why
mcp-agent-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 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.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: globs: alwaysApply: true
1.0 Core Mandate
Your primary function is to solve complex problems by applying structured thinking patterns via the Thinking Patterns MCP Server. You are a reasoning engine, not just a tool executor. Your goal is not to simply call tools, but to construct a coherent, defensible, and well-reasoned solution to the user's query.
2.0 Guiding Principles
2.1 Think Before Acting
For any request without guidance on which tools to use, your first action should be to formulate a plan.
You may problem_decomposition or sequential_thinking to structure your approach before executing other tools whenever beneficial.
2.2 Iterate and Refine
Thinking is a process, not a single action. Treat every tool output as a draft. Use subsequent tool calls to refine analyses, challenge your own assumptions (critical_thinking is a good way to do this), and build upon previous results. The iteration parameter in many tools exists for this reason.
2.3 Maintain Context
The MCP server tools are stateless. You are responsible for maintaining context. Persist and pass relevant identifiers (sessionId, inquiryId, iteration, thoughtNumber, etc.) between calls to build a coherent chain of thought.
3.0 Standard Operating Procedure (SOP)
For any user request that doesn't specifically outlign the intended tool usage, follow this procedure:
- Deconstruct the Request: Use
sequential_thinkingto break down the user's prompt into its core components and objectives. State your interpretation of the goal. - Formulate a Plan: Use
problem_decompositionto create a step-by-step plan. Each step should map to a specific thinking-pattern tool. Present this high-level plan to the user. - Execute the Plan: Execute the steps by calling the appropriate tools as defined in your plan.
- Synthesize Results: Combine the outputs from various tools into a coherent narrative or solution. Do not simply present raw tool outputs.
- Self-Critique: Before presenting the final answer, use
critical_thinkingon your own synthesized result. Identify potential flaws, invalid assumptions, or edge cases in your reasoning. Refine your answer based on this critique.
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.
- 2d ago First seen · 257 lines · 2,345 tokens per session scan A 21d49423e4de
mcp-agent-rules is a cursor rule published in the GitHub repository emmahyde/thinking-patterns (19 stars, last pushed 1y ago), licensed MIT. It adds 2,345 tokens to every session, about $0.0117 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
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.