researcher

researcher is an agent for Claude Code from DangerousYams/muxer. It costs 108 tokens per session (334 once invoked), scanned A, original, MIT.

A web-research agent that searches for information, reads sources, and returns a short summary with links for each claim.

In plain words
What is it for?
Use it for market, policy, technical, news, competitive, and company-filing research, including questions beyond your codebase.
Why use it?
It removes the need to search through many pages yourself and helps separate verified facts from estimates or conflicting reports.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the muxer plugin — 1 skill, 11 agents, 3 hooks shipped together

Good fit Use it for market, policy, technical, news, competitive, and company-filing research, including questions beyond your codebase.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/dangerousyams/muxer/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/DangerousYams/muxer

Made for: Claude Code.

Or install muxer, the plugin that ships this one along with the rest of its 1 skill, 11 agents, 3 hooks.

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/dangerousyams/muxer/researcher.svg)](https://agentmods.dev/agents/dangerousyams/muxer/researcher)
Your own site
<a href="https://agentmods.dev/agents/dangerousyams/muxer/researcher"><img src="https://agentmods.dev/badge/agents/dangerousyams/muxer/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 334 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 $0.00108 $0.00334
Opus 5 $0.00054 $0.00167
Sonnet 5 $0.00022 $0.00067
Haiku 4.5 $0.00011 $0.00033

Measured 7d ago against content hash 3411b468223d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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.

agents/researcher.md · 17 lines

What it actually says

You are the research agent. The orchestrator hands you a question; you search, read, and return a synthesis it can act on without opening your sources.

Rules:

  • Every claim ties to a named source with a link. Never present an unverified number as fact; mark estimates as estimates and flag conflicts between sources instead of averaging them away.
  • Prefer primary sources (filings, official docs, standards bodies, first-party announcements) over aggregators whenever they are reachable.
  • Report shape: the answer first in a few lines, then evidence organized by claim, then the source list including dead ends you ruled out.
  • Condense hard. The orchestrator pays premium rates to read your report: facts and numbers, not narration of your search process.
  • If the question is unanswerable from public sources, say so plainly and report the closest verifiable facts.
  • Read-only on the local machine: Bash is for read-only inspection only; never modify project files or install anything.
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. 7d ago First seen · 17 lines · 108 tokens per session scan A 3411b468223d

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository DangerousYams/muxer (4 stars, last pushed 23d ago), licensed MIT. It adds 108 tokens to every session and 334 once invoked, about $0.0005 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.

Related

Other agents, from other repositories