A research command that checks factual claims in a PR/FAQ and finds supporting evidence. It also prepares bibliography entries and citations in BibLaTeX, a format used by LaTeX documents.

Use it for a whole PR/FAQ, a specific claim, or a topic; it saves the findings for later reuse and can suggest updates to the document.

It helps replace unsupported claims and citation placeholders with sources, while recording gaps where evidence could not be found.

research — Command for coding agents by punt-labs: A research command that checks factual claims in a…

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 commands/punt-labs/prfaq/research

Clone the repo

git clone --depth 1 https://github.com/punt-labs/prfaq

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/punt-labs/prfaq/research.svg)](https://agentmods.dev/commands/punt-labs/prfaq/research)

Your own site

<a href="https://agentmods.dev/commands/punt-labs/prfaq/research"><img src="https://agentmods.dev/badge/commands/punt-labs/prfaq/research.svg" alt="Measured on agentmods" height="20"></a>

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 374 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.

Model	Per session	Once invoked
Fable 5	$0.00012	$0.00374
Opus 5	$0.00006	$0.00187
Sonnet 5	$0.00002	$0.00075
Haiku 4.5	$0.00001	$0.00037

Measured 4d ago against content hash db8f3dfb05c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research 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 4d 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/commands/research.md · 29 lines

What it actually says

Research Evidence for PR/FAQ

Invoke the researcher agent to find evidence for claims in a PR/FAQ document.

Steps

Determine the input. If $ARGUMENTS specifies a .tex file path, pass it to the researcher to extract and verify all [CITATION NEEDED] markers and factual claims. If it specifies a claim or topic, pass that directly. If no argument is given, search for prfaq.tex in the project root and pass its path.
Invoke the researcher agent using the Task tool with subagent_type: "prfaq:researcher". Pass the file path, claim, or topic in the prompt.
Present the results to the user. The researcher returns:
- Evidence found per claim (with verdict: supported/unsupported/contradicted)
- Bibliography entries ready to append to the .bib file
- Research gaps where no evidence was found
The researcher automatically saves its findings to ./research/research-YYYY-MM-DD-TOPIC.md. Future runs reuse cached results instead of re-searching the web.
Offer to update the document. If the researcher found new sources:
- Append new .bib entries to the bibliography file
- Add \cite{} commands to the .tex file where claims now have sources
- Replace [CITATION NEEDED] markers with proper citations
- Recompile the PDF

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.

4d ago First seen · 29 lines · 12 tokens per session scan A db8f3dfb05c7

Subscribe to this mod's changes

research is a command published in the GitHub repository punt-labs/prfaq (25 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 374 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 2026-08-30.

LaTeX Research beta claude-code-plugin pdf-generation product-discovery

research

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Research Evidence for PR/FAQ

Steps

What this file has done since we first saw it

Other commands, from other repositories

oracle-dev

refine-dev

refine

contracts-dev

code2model-dev

partition-dev