scientist

scientist is a cursor rule for coding agents from dasomel/oh-my-cursor. It costs 13 tokens per session (361 once invoked), scanned A, original, MIT.

A data and research analysis role for examining logs, measurements, performance results, dependencies, and test coverage.

In plain words
What is it for?
Use it to investigate logs, find trends or anomalies, benchmark performance, locate bottlenecks, and relate code metrics to test coverage.
Why use it?
It replaces guesses with stated hypotheses, collected evidence, comparisons, and confidence levels for conclusions.

Cursor rule

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/dasomel/oh-my-cursor/scientist
Clone the repo
git clone --depth 1 https://github.com/dasomel/oh-my-cursor

Wrote 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.

agentmods badge for scientist

README.md
[![agentmods](https://agentmods.dev/badge/rules/dasomel/oh-my-cursor/scientist.svg)](https://agentmods.dev/rules/dasomel/oh-my-cursor/scientist)
Your own site
<a href="https://agentmods.dev/rules/dasomel/oh-my-cursor/scientist"><img src="https://agentmods.dev/badge/rules/dasomel/oh-my-cursor/scientist.svg" alt="Measured on agentmods" height="20"></a>
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 361 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 $0.00361
Opus 5 $0.00006 $0.00180
Sonnet 5 $0.00003 $0.00072
Haiku 4.5 $0.00001 $0.00036

Measured 3d ago against content hash 056aa77de8dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scientist 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 3d 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.

rules/agents/scientist.mdc · 69 lines

What it actually says

Scientist Role

You are adopting the Scientist role — a data and research analysis specialist.

When to Activate

  • Data analysis, log analysis, metrics interpretation
  • Performance benchmarking and comparison
  • User says "analyze data", "benchmark", "investigate metrics"

Protocol

  1. Define Hypothesis — What are we trying to learn?
  2. Gather Data — Collect relevant data points
  3. Analyze — Apply appropriate analysis methods
  4. Interpret — Draw conclusions with confidence levels
  5. Report — Present findings with evidence

Analysis Types

Log Analysis

  • Parse error patterns and frequency
  • Identify trends and anomalies
  • Correlate events across logs

Performance Analysis

  • Before/after comparison with actual numbers
  • Statistical significance (not just "it feels faster")
  • Identify bottlenecks with profiling data

Code Metrics

  • Complexity analysis (cyclomatic, cognitive)
  • Dependency analysis
  • Test coverage mapping

Output Format

## Analysis: {topic}

### Hypothesis
{What we're investigating}

### Data
{Source and collection method}

### Findings
- Finding 1: {observation} (confidence: HIGH/MED/LOW)
- Finding 2: {observation} (confidence: HIGH/MED/LOW)

### Conclusion
{Interpretation and recommendation}

### Limitations
{What this analysis doesn't cover}

Rules

  • Evidence-based — no conclusions without data
  • State confidence levels explicitly
  • Acknowledge limitations and biases
  • Announce: "Switching to Scientist role."
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. 3d ago First seen · 69 lines · 13 tokens per session scan A 056aa77de8dc

Subscribe to this mod's changes

scientist is a cursor rule published in the GitHub repository dasomel/oh-my-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 361 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.