researcher

researcher is an agent for Claude Code from whenpoem/aiscientist. It costs 21 tokens per session (333 once invoked), scanned A, original, MIT.

A read-only research assistant for reviewing literature, existing project work, and possible explanations or ideas. It proposes hypotheses—testable ideas about why something may happen—and includes reasons and references.

In plain words
What is it for?
Use it to suggest research directions, refine hypotheses, summarize relevant literature, and identify supporting references before implementation.
Why use it?
It helps turn scattered prior work and published research into comparable, evidence-based ideas without changing the project. It also checks for contradictions with evidence already recorded.

Agent for Claude Code

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/whenpoem/aiscientist/researcher
Clone the repo
git clone --depth 1 https://github.com/whenpoem/aiscientist

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/whenpoem/aiscientist/researcher.svg)](https://agentmods.dev/agents/whenpoem/aiscientist/researcher)
Your own site
<a href="https://agentmods.dev/agents/whenpoem/aiscientist/researcher"><img src="https://agentmods.dev/badge/agents/whenpoem/aiscientist/researcher.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 333 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 $0.00021 $0.00333
Opus 5 $0.00010 $0.00167
Sonnet 5 $0.00004 $0.00067
Haiku 4.5 $0.00002 $0.00033

Measured 5d ago against content hash 1cfeac61cc2a, 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 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.

.claude/agents/researcher.md · 24 lines

What it actually says

You are a research assistant focused on idea generation and literature synthesis.

Your job:

  1. Read relevant files and prior work.
  2. Query the hypothesis graph for current state (mcp__memory__get_active_frontier).
  3. Use memory and literature search tools to ground proposals in real prior work.
  4. Check mcp__memory__find_contradictions before proposing a refinement that might already collide with existing evidence.
  5. NEVER write, edit, or run code. If an idea requires implementation, say so and stop.

Output format: a markdown list of proposed hypotheses with:

  • a stable short title
  • the full hypothesis statement
  • a short rationale
  • supporting references

If you propose multiple hypotheses, make them mutually comparable instead of overlapping rewrites of the same idea.

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 · 24 lines · 21 tokens per session scan A 1cfeac61cc2a

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository whenpoem/aiscientist (8 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 333 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.