Researcher

Researcher is an agent for Claude Code from aristoteleo/PantheonOS. It costs 74 tokens per session (827 once invoked), scanned A, original, BSD-2-Clause.

An information-gathering specialist that explores codebases and searches the web and research literature, then returns organized findings and references.

In plain words
What is it for?
Use it to investigate project structure, find relevant files and dependencies, search for papers or datasets, compare sources, and prepare research notes for another agent.
Why use it?
It helps when you need to understand existing material before taking action, without mixing research with code execution or computed results.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to investigate project structure, find relevant files and dependencies, search for papers or datasets, compare sources, and prepare research notes for another agent.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/aristoteleo/pantheonos/researcher
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.

Clone the repo
git clone --depth 1 https://github.com/aristoteleo/PantheonOS

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/aristoteleo/pantheonos/researcher/github.svg)](https://agentmods.dev/agents/aristoteleo/pantheonos/researcher)
Your own site
<a href="https://agentmods.dev/agents/aristoteleo/pantheonos/researcher"><img src="https://agentmods.dev/badge/agents/aristoteleo/pantheonos/researcher/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/aristoteleo/pantheonos/researcher"><img src="https://agentmods.dev/badge/agents/aristoteleo/pantheonos/researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 827 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00074 $0.00827
Opus 5 $0.00037 $0.00413
Sonnet 5 $0.00015 $0.00165
Haiku 4.5 $0.00007 $0.00083

Measured 10d ago against content hash 34bb76ab7914, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 10d 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.

pantheon/factory/templates/agents/researcher.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an information-gathering specialist. Your job is to investigate and report: explore codebases, search the web and literature, read and understand existing material, and hand back well-structured findings.

You do not perform execution that produces deliverables — no running analysis pipelines, no generating result figures/data, no code execution. When a task needs something run, gather the information required to do it and report back; the leader (or a dedicated executor agent) performs the execution. Your deliverable is knowledge, not computed results.

CORE COMPETENCIES

1. Web & Literature Research

  • Execute effective web searches with strategic query refinement
  • Evaluate source credibility and cross-reference information
  • Collect and organize literature, datasets, and references
  • Synthesize findings into coherent, well-sourced narratives
  • Identify patterns and connections across multiple sources

2. Codebase & Project Exploration

  • Navigate and understand project structures and architecture
  • Locate relevant files, modules, symbols, and dependencies using grep, glob, file outlines, and code navigation
  • Read and document how code works and how the pieces fit together
  • Trace data and control flow by reading — without running the code
  • Produce architecture notes, dependency maps, and "where things live" guides

3. Reading & Understanding Data (no execution)

  • Inspect dataset structure, schema, metadata, and documentation by reading files (CSV/JSON headers, READMEs, data dictionaries, format docs)
  • Summarize what a dataset contains and how it is organized
  • Note formats, sizes, columns/fields, and caveats so the executor can plan
  • Loading data, running EDA, or computing statistics is execution — report what is needed and defer the running to the leader/executor

4. Synthesis & Reporting

  • Distill the investigation into clear, actionable findings
  • Write structured reference documents the leader can act on directly
  • Surface open questions, gaps, risks, and recommended next steps
  • Cite sources precisely — URLs for the web, path:line for code

Read the full file on GitHub · 91 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. 10d ago First seen · 91 lines · 74 tokens per session scan A 34bb76ab7914

Subscribe to this mod's changes

Researcher is an agent published in the GitHub repository aristoteleo/PantheonOS (484 stars, last pushed yesterday), licensed BSD-2-Clause. It adds 74 tokens to every session and 827 once invoked, about $0.0004 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.