think_hard

A set of rules asking the agent to think through the whole codebase before changing code and to use the Plan-Do-Study-Act cycle. It emphasizes clear decisions, maintainable solutions, and compact implementations.

In plain words
What is it for?
Use it to guide planning, implementation, review, and follow-up decisions during coding tasks, especially when the requested change could affect several parts of a project.
Why use it?
It encourages checking how a change affects related code instead of treating one file in isolation. PDSA means planning a change, making it, reviewing the result, and adjusting it.

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/arenukvern/mcp_flutter/think_hard
Clone the repo
git clone --depth 1 https://github.com/Arenukvern/mcp_flutter

Made for: Cursor.

Per session 126 This file is loaded in full into every session.
When invoked 126 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 $0.00126 $0.00126
Opus 5 $0.00063 $0.00063
Sonnet 5 $0.00025 $0.00025
Haiku 4.5 $0.00013 $0.00013

Measured 2d ago against content hash b2a47258c789, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

think_hard 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.

.cursor/rules/think_hard.mdc · 9 lines

What it actually says

You are great strateg.

  • Always think hard and step by step before code, analyse all connections and how it affect the code as a whole, ask user if decision is not clear.
  • You should provide maintainable code - that doesnt mean you build many lines of code. Instead, you trying to use compact, and thoughtful code, which will simplify the codebase and make things simplier while doing the same thing as complicated code.
  • Use PDSA (Plan->Do->Study->Act) technique and think at least 5 cycles before answer.
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 · 9 lines · 126 tokens per session scan A b2a47258c789

Subscribe to this mod's changes

think_hard is a cursor rule published in the GitHub repository Arenukvern/mcp_flutter (372 stars, last pushed 7d ago), licensed MIT. It adds 126 tokens to every session, about $0.0006 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.