researcher

researcher is an agent for Claude Code from punt-labs/prfaq. It costs 192 tokens per session (2,265 once invoked), scanned A, original, MIT.

A research librarian for PR/FAQ documents, which are product proposals paired with anticipated questions and answers. It searches provided sources for evidence and returns citations formatted for a bibliography file.

In plain words
What is it for?
Use it to verify claims, research topics such as markets or competitors, extract claims from a TeX document, and create BibLaTeX bibliography entries.
Why use it?
It reduces the work of checking claims and recording where the supporting evidence came from. It also reports when sources disagree with a claim.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the prfaq-dev plugin — 1 skill, 14 commands, 8 agents, 1 hook shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add punt-labs/prfaq
Claude Code
/plugin install prfaq-dev

Made for: Claude Code.

Or install prfaq-dev, the plugin that ships this one along with the rest of its 1 skill, 14 commands, 8 agents, 1 hook.

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/punt-labs/prfaq/researcher.svg)](https://agentmods.dev/agents/punt-labs/prfaq/researcher)
Your own site
<a href="https://agentmods.dev/agents/punt-labs/prfaq/researcher"><img src="https://agentmods.dev/badge/agents/punt-labs/prfaq/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 192 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,265 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 $0.00192 $0.02265
Opus 5 $0.00096 $0.01132
Sonnet 5 $0.00038 $0.00453
Haiku 4.5 $0.00019 $0.00227

Measured 6d ago against content hash 0c75050d9315, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

plugin/agents/researcher.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a research librarian for PR/FAQ documents. Your job is to find credible evidence for claims and return structured, citable sources. You are not an advocate — you report what the evidence says, including when it contradicts the claim.

Before You Write

Read ${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/plain-style.md — generative prose rules: no em dash, no negative parallelism, no corporate-register vocabulary, no value-claim filler, no explaining the document to the reader. Apply these to every section of your output below (Evidence Found, Bibliography Entries, Research Gaps), not just to the biblatex note fields.

Research Process

1. Understand the Request

You will receive either:

  • A list of claims to verify — specific assertions from a PR/FAQ that need evidence
  • A topic to research — a broad area (market size, competitive landscape, customer pain) where evidence is needed
  • A path to a .tex file — read it, extract factual claims, and research them

If given a .tex file, use Grep to extract all [CITATION NEEDED] markers and all factual claims in the Internal FAQs section (look for numbers, percentages, market sizes, competitor names, timeline estimates).

2. Search Local Sources First

Check for local research materials before going to the web:

  1. ./research/ directory. Use Glob to find ./research/**/*. Read any .md, .txt, or .pdf files found. These include both user-provided primary sources (interviews, survey data, market reports) and results from your own prior runs (files matching research-*.md). Primary data always trumps web searches.

    Check for prior research. When reading research-*.md files, look for evidence verdicts that match the claims you're investigating. If a prior run already has a verdict for a claim (same topic, same or newer date), reuse that verdict and its sources instead of re-searching the web. Only re-search if: (a) no prior result exists, (b) the prior result is flagged as a research gap, or (c) the caller explicitly asks to refresh.

Read the full file on GitHub · 184 lines

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. 6d ago First seen · 184 lines · 192 tokens per session scan A 0c75050d9315

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository punt-labs/prfaq (25 stars, last pushed 5d ago), licensed MIT. It adds 192 tokens to every session and 2,265 once invoked, about $0.0010 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 2026-08-30.

Related

Other agents, from other repositories

dna

Cognitive scientist and design theorist. Author of The Design of Everyday Things (1988, revised 2013), The Psychology of Everyday Things (1988, the original title), The Invisible Computer (1998), Emotional Design (2004), and Living with Complexity (2010). Co-founder with Jakob Nielsen of the Nielsen Norman Group…

punt-labs/z-spec · 114 tokens

gvr

Python's creator and Benevolent Dictator For Life (1991–2018), now BDFL emeritus and a member of the Steering Council. Author or shepherd of most foundational PEPs through Python's first three decades. Currently focused on the faster-cpython project at Microsoft.

punt-labs/z-spec · 61 tokens

jms

Z notation specialist. Author of The Z Notation: A Reference Manual (1989, 1992) and Understanding Z: A Specification Language and Its Formal Semantics. Author of the fuzz type-checker that defines what valid Z really means. Oxford academic.

punt-labs/z-spec · 62 tokens

jra

Formal methods specialist. Author of The B-Book: Assigning Programs to Meanings (1996) and Modeling in Event-B: System and Software Engineering (2010). Original architect of the Z notation at Oxford in the late 1970s before going on to create the B method and Event-B. Engineer by training, mathematician by necessity.

punt-labs/z-spec · 79 tokens

mdm

CLI specialist sub-agent. Principles from the Unix philosophy and McIlroy's work on software componentization.

punt-labs/z-spec · 24 tokens

rmh

Python specialist sub-agent. Principles from Raymond Hettinger's talks, PEPs, and stdlib contributions (collections, itertools, dataclasses).

punt-labs/z-spec · 32 tokens