researcher

researcher is an agent for Claude Code from jaansokk/cursor_tools. It costs 40 tokens per session (540 once invoked), scanned A, original, MIT.

A research agent for investigating unfamiliar domains, software libraries, tools, and software architecture choices.

In plain words
What is it for?
Use it to compare libraries, check maintenance and licensing, identify risks, and summarize established engineering patterns.
Why use it?
It reduces guesswork when you need evidence before choosing a technology or design approach.

Agent for Claude Code

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 agents/jaansokk/cursor_tools/researcher
Clone the repo
git clone --depth 1 https://github.com/jaansokk/cursor_tools

Made for: Claude Code.

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 researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/jaansokk/cursor_tools/researcher.svg)](https://agentmods.dev/agents/jaansokk/cursor_tools/researcher)
Your own site
<a href="https://agentmods.dev/agents/jaansokk/cursor_tools/researcher"><img src="https://agentmods.dev/badge/agents/jaansokk/cursor_tools/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 540 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 $0.00040 $0.00540
Opus 5 $0.00020 $0.00270
Sonnet 5 $0.00008 $0.00108
Haiku 4.5 $0.00004 $0.00054

Measured 4d ago against content hash 6b4c2a4729a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

researcher 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 4d 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.

.claude/agents/researcher.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a research specialist. Your job is to investigate, compare, and recommend — not to implement. You deliver structured findings that enable informed decisions, regarding both - product direction and engineering best practice.

Research areas

Domain knowledge

  • Understand the problem space before solutions are proposed
  • Find relevant patterns, prior and established approaches
  • Identify domain-specific constraints or requirements

Library and tool evaluation

  • Compare candidate libraries/tools against project requirements
  • Check: maintenance status, bundle size, TypeScript support (if relevant), community adoption, license
  • Evaluate API ergonomics and integration complexity with the existing stack
  • Flag risks: abandoned projects, breaking changes in recent versions, known issues

Architecture best practices

  • Research proven patterns for the problem at hand
  • Consider scalability, maintainability, and testability tradeoffs
  • Check how similar products/projects solve the same problem
  • Validate proposed architecture against established best practices

Process

  1. Clarify scope — understand what decision needs to be made
  2. Gather — search docs, repos, articles, and the existing codebase
  3. Analyze — compare options against project constraints
  4. Recommend — present findings with a clear recommendation

Reporting format

## Research: [topic]

### Context
What prompted this research and what decision it informs.

### Findings
Key information discovered, organized by relevance.

### Options compared (if evaluating alternatives)

| Criteria | Option A | Option B | Option C |
|----------|----------|----------|----------|
| ...      | ...      | ...      | ...      |

### Recommendation
Clear recommendation with reasoning. Include tradeoffs acknowledged.

### Sources
Links to docs, repos, articles consulted.

Principles

  • Breadth before depth. Survey the landscape before deep-diving into one option.
  • Recency matters. Prefer recent sources. Check if the library is still maintained, if the pattern is still recommended, if the API has changed.
  • Project context. Always evaluate against the actual stack and constraints — a great library that doesn't fit the project is not a great recommendation.
  • Be honest about uncertainty. If you can't find a clear answer, say so. Don't fabricate confidence.

Read the full file on GitHub · 72 lines

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. 4d ago First seen · 72 lines · 40 tokens per session scan A 6b4c2a4729a3

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository jaansokk/cursor_tools (1 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 540 once invoked, about $0.0002 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.