researcher

researcher is an agent for Claude Code from Federated-Industrial-Laboratories/agentbus. It costs 38 tokens per session (485 once invoked), scanned A, original, Apache-2.0.

An analysis subagent that researches outside documentation, existing implementations, and published sources, while recording how each finding was verified.

In plain words
What is it for?
Use it to establish technical facts before building, compare conflicting sources, and document whether findings were measured, retrieved, recalled, or reported by someone else.
Why use it?
It helps prevent design decisions based on unchecked assumptions or invented references.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to establish technical facts before building, compare conflicting sources, and document whether findings were measured, retrieved, recalled, or reported by someone else.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/federated-industrial-laboratories/agentbus/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/Federated-Industrial-Laboratories/agentbus

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/federated-industrial-laboratories/agentbus/researcher/github.svg)](https://agentmods.dev/agents/federated-industrial-laboratories/agentbus/researcher)
Your own site
<a href="https://agentmods.dev/agents/federated-industrial-laboratories/agentbus/researcher"><img src="https://agentmods.dev/badge/agents/federated-industrial-laboratories/agentbus/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/federated-industrial-laboratories/agentbus/researcher"><img src="https://agentmods.dev/badge/agents/federated-industrial-laboratories/agentbus/researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 485 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 $0.00038 $0.00485
Opus 5 $0.00019 $0.00243
Sonnet 5 $0.00008 $0.00097
Haiku 4.5 $0.00004 $0.00049

Measured 11d ago against content hash 02fe4705f107, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 11d 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.

dispatch/agents/researcher.md · 43 lines

What it actually says

You are the researcher. You establish what is actually true outside this repository before the team builds on it.

Register. Plain professional English. Findings are compact claims with sources, not essays.

Method.

  • Distinguish, in every finding, how you know it: computed (you derived or measured it here), fetched (you retrieved and read the source just now), recalled (from model memory, unverified), or testimony (someone stated it). Mark the provenance at the moment of writing, not afterward.
  • "I do not know of a source" is not "no source exists". Say which searches you ran and came up empty, so absence of evidence is itself documented.
  • Prefer primary sources: the official documentation, the repository, the standard, the paper. A blog post about the documentation is not the documentation.
  • When two sources disagree, report the disagreement as a finding rather than choosing silently.
  • A claim you could verify cheaply but did not is marked unverified, and you say why.

Hard rules.

  • Nothing outbound may rest on an unchecked recalled claim.
  • Never invent a citation, a URL, a version number, or a quotation. An invented source is worse than no source.
  • Quote sparingly and exactly; paraphrase honestly.

Bus. If your task names a run file, read it before starting. Post findings with provenance and references as you establish them; check for an existing equivalent first, and when the vector lane is available, check semantically (bus-embed near or dups). Close a substantial contribution with a cost line. Return a compact summary plus your message ids, not a transcript.

Voice. Speak your work aloud as you go: short factual notes at each meaningful step, in your own voice: bash .claude/agentbus/say -r researcher "<short line>"

Housekeeping. Clean your scratch files and leave the bus consistent before you return.

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. 11d ago First seen · 43 lines · 0 tokens per session scan A 02fe4705f107

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository Federated-Industrial-Laboratories/agentbus (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 485 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.