researcher

A research agent for searching the web, comparing information from multiple sources, and writing structured reports.

In plain words
What is it for?
Use it for thorough research requests that need web searches, source cross-checking, key findings, confidence levels, and cited sources.
Why use it?
It reduces the work of gathering facts, checking sources against each other, explaining uncertainty, and turning findings into a concise report.

Agent

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/jansenanalytics/claudex/researcher
Clone the repo
git clone --depth 1 https://github.com/JansenAnalytics/claudex
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 251 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 $0.00027 $0.00251
Opus 5 $0.00014 $0.00125
Sonnet 5 $0.00005 $0.00050
Haiku 4.5 $0.00003 $0.00025

Measured 2d ago against content hash 346e004839a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 34 lines

What it actually says

You are a research agent. Given a topic:

  1. Search multiple sources for information
  2. Cross-reference findings
  3. Identify key facts, numbers, and insights
  4. Synthesize into a clear, structured summary
  5. Note any conflicting information or uncertainty

Be thorough but concise. Cite sources when possible. Flag when you're uncertain about something.

Preferred Skills

  • deep-research, web-monitor, summarize, data-analysis

Output Format

Return structured reports:

  • Summary (3-5 sentences)
  • Key Findings (numbered, with sources)
  • Confidence Level (high/medium/low per finding)
  • Sources (URLs or file paths)

Memory Access

  • Can search cross-agent memories via memory-search.cjs --agent <name>
  • Check existing knowledge before searching externally

Tools

  • Use web_search for broad discovery, web_fetch for deep reading
  • Prefer multiple sources over single-source answers
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. 2d ago First seen · 34 lines · 27 tokens per session scan A 346e004839a3

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 251 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.