researcher

researcher is an agent for Claude Code from griddynamics/rosetta. It costs 22 tokens per session (347 once invoked), scanned A, a copy of researcher, Apache-2.0.

A research agent that investigates a defined topic systematically and records findings with supporting references.

In plain words
What is it for?
Use it for deep technical or feature research that needs a written report, research prompt, and progress tracking.
Why use it?
It helps avoid unsupported conclusions by organizing exploration, checking information, and documenting the research process.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions subagents.

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/griddynamics/rosetta/researcher-profile-lightweight-only-overwrite
Clone the repo
git clone --depth 1 https://github.com/griddynamics/rosetta

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/griddynamics/rosetta/researcher-profile-lightweight-only-overwrite.svg)](https://agentmods.dev/agents/griddynamics/rosetta/researcher-profile-lightweight-only-overwrite)
Your own site
<a href="https://agentmods.dev/agents/griddynamics/rosetta/researcher-profile-lightweight-only-overwrite"><img src="https://agentmods.dev/badge/agents/griddynamics/rosetta/researcher-profile-lightweight-only-overwrite.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 347 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 5.1 $0.00022 $0.00347
Opus 5 $0.00011 $0.00173
Sonnet 5 $0.00004 $0.00069
Haiku 4.5 $0.00002 $0.00035

Measured 3d ago against content hash cc542cde5ef9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 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.

Origin

This is a copy

86% identical to researcher — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

instructions/r3/core/agents/researcher~profile-lightweight-only~overwrite~.md · 56 lines

What it actually says

Senior research specialist. Systematic, grounded, accuracy-first deep research with meta-prompting approach.

  • All Rosetta prep steps MUST be FULLY completed, load-project-context skill loaded and fully executed
  • CONTEXT.md, ARCHITECTURE.md, IMPLEMENTATION.md read
  • Research scope and feature name provided by orchestrator
  1. Confirm research scope from orchestrator input.
  2. Apply research skill.
  3. If scope is unclear or research reveals unexpected complexity, MUST STOP, EXPLAIN REASONS, and LET PARENT decide.

<skills_available>

  • USE SKILL research
  • USE SKILL reasoning

</skills_available>

<output_template>

Research output: docs/<feature>-research.md State tracking: research-state.md in FEATURE TEMP folder Research prompt: research-prompt.md in FEATURE PLAN folder

</output_template>

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 · 56 lines · 22 tokens per session scan A cc542cde5ef9

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository griddynamics/rosetta (342 stars, last pushed 2d ago), licensed Apache-2.0. It adds 22 tokens to every session and 347 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to researcher, differing in 6 lines, and is treated as a copy.