review

review is a command for coding agents from punt-labs/prfaq. It costs 12 tokens per session (280 once invoked), scanned A, original, MIT.

A peer review of a PR/FAQ against product-writing and decision-quality principles. It reads the document’s stage to set the expected level of evidence.

In plain words
What is it for?
Use it to get a pass, iterate, or reject assessment, with specific issues, strengths, and ordered next steps.
Why use it?
It identifies weaknesses that could make the proposal unclear, poorly supported, or not ready for a decision.

Command

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

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/review
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.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/commands/punt-labs/prfaq/review.svg)](https://agentmods.dev/commands/punt-labs/prfaq/review)
Your own site
<a href="https://agentmods.dev/commands/punt-labs/prfaq/review"><img src="https://agentmods.dev/badge/commands/punt-labs/prfaq/review.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 280 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 $0.00012 $0.00280
Opus 5 $0.00006 $0.00140
Sonnet 5 $0.00002 $0.00056
Haiku 4.5 $0.00001 $0.00028

Measured 5d ago against content hash c834a5c88448, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review 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.

plugin/commands/review.md · 24 lines

What it actually says

Peer Review PR/FAQ

Invoke the peer-reviewer agent to critically evaluate a PR/FAQ document against Working Backwards principles and the Kahneman decision quality framework.

Steps

  1. Find the document. If $ARGUMENTS specifies a path, use it. Otherwise, search for prfaq.tex in the project root.

  2. Launch the peer-reviewer agent using the Task tool with subagent_type: "prfaq:peer-reviewer". Pass the file path in the prompt. The peer reviewer reads \prfaqstage{} from the document and calibrates its evidence expectations accordingly.

  3. Present the results to the user. The peer reviewer returns:

    • Overall assessment (PASS / ITERATE / REJECT)
    • Critical issues and warnings with specific locations and recommendations
    • Document strengths
    • Ordered next steps
  4. Offer to iterate. If the review flags issues, ask the user which they want to address. For accepted issues, make the revisions to the .tex file, recompile, and offer to re-run the review.

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 · 12 tokens per session scan A c834a5c88448

Subscribe to this mod's changes

review is a command published in the GitHub repository punt-labs/prfaq (25 stars, last pushed 5d ago), licensed MIT. It adds 12 tokens to every session and 280 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.