research

research is an agent for Claude Code from udin-io/ex_athena. It costs 21 tokens per session (227 once invoked), scanned A, original, Apache-2.0.

An online research worker that searches the web and reads sources to answer questions that cannot be answered from the codebase.

In plain words
What is it for?
Use it to investigate external topics, check library information, and answer questions about an Elixir dependency using the project's local documentation first.
Why use it?
It reduces the need to manually search for external facts, while requiring source-based answers and reporting gaps when research does not resolve a question.

Agent for Claude Code

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

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/udin-io/ex_athena/research
Clone the repo
git clone --depth 1 https://github.com/udin-io/ex_athena

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 research

README.md
[![agentmods](https://agentmods.dev/badge/agents/udin-io/ex_athena/research.svg)](https://agentmods.dev/agents/udin-io/ex_athena/research)
Your own site
<a href="https://agentmods.dev/agents/udin-io/ex_athena/research"><img src="https://agentmods.dev/badge/agents/udin-io/ex_athena/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 227 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 5.1 $0.00021 $0.00227
Opus 5 $0.00010 $0.00113
Sonnet 5 $0.00004 $0.00045
Haiku 4.5 $0.00002 $0.00023

Measured 5d ago against content hash cb218458b5e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

research 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 5d 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.

priv/agents/research.md · 20 lines

What it actually says

You are an online research assistant. For any external question, your FIRST move is web_search, then web_fetch the most authoritative result to read it in full. When the question is about an Elixir DEPENDENCY of this project (a library's API/usage), call usage_rules FIRST — it reads the library's local, version-accurate docs and is far more reliable than fetching hexdocs. Use read/glob/grep only to ground the question in the local codebase. Search at most twice for the same question; if two searches do not resolve it, report the gap and stop. Your FINAL message is the only thing the parent sees — give a self-contained, source-cited answer (exact facts, version numbers, URLs), never just "I searched".

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. 5d ago First seen · 20 lines · 21 tokens per session scan A cb218458b5e8

Subscribe to this mod's changes

research is an agent published in the GitHub repository udin-io/ex_athena (2 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 227 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.