02-reasoning

A reasoning rule for difficult analysis, debugging, and understanding how code works. It guides the review through observations, possible explanations, detailed analysis, conclusions, and fixes.

In plain words
What is it for?
It is for complex debugging, execution-flow tracing, performance investigations, logical analysis, and checking possible security effects.
Why use it?
It helps avoid guessing when a problem has several possible causes or when the effects of a code change are hard to trace.

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/jonafrank/cursor-multi-model-config/02-reasoning
Clone the repo
git clone --depth 1 https://github.com/jonafrank/cursor-multi-model-config

Made for: Cursor.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 288 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00013 $0.00288
Opus 5 $0.00006 $0.00144
Sonnet 5 $0.00003 $0.00058
Haiku 4.5 $0.00001 $0.00029

Measured 2d ago against content hash 4c669035166c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

02-reasoning 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/02-reasoning.mdc · 44 lines

What it actually says

Reasoning Mode

This rule activates for tasks requiring deep analysis and logical reasoning.

When This Applies

  • Debugging complex issues
  • Understanding why code behaves a certain way
  • Analyzing performance problems
  • Tracing through execution flows
  • Evaluating security implications

Model Recommendation

Check .cursor/model-profiles/current-profile.json for the reasoning model.

Typical models for reasoning:

  • claude-4.5-opus-high (completeness/default profile)
  • claude-4.5-haiku (cost_minimized/fallback profile)

Reasoning Guidelines

  1. Gather context: Read relevant code before drawing conclusions
  2. Form hypotheses: Consider multiple possible explanations
  3. Trace systematically: Follow execution paths step by step
  4. Validate assumptions: Check that premises are correct
  5. Explain clearly: Make the reasoning chain visible

Output Format

For reasoning tasks, structure your response as:

  1. Observation: What we're seeing
  2. Hypothesis: Possible explanations
  3. Analysis: Step-by-step investigation
  4. Conclusion: What we determined
  5. Solution: Recommended fix (if applicable)
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 · 44 lines · 13 tokens per session scan A 4c669035166c

Subscribe to this mod's changes

02-reasoning is a cursor rule published in the GitHub repository jonafrank/cursor-multi-model-config (5 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 288 once invoked, about $0.0001 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 2026-08-31.