paper2pr: Agent for Claude Code

.claude/agents/pedagogy-reviewer.md

pedagogy-reviewer is an agent for Claude Code from alohays/paper2pr. It costs 57 tokens per session (2,247 once invoked), scanned A, original, MIT.

A review agent for the teaching quality of slide decks. It examines the audience, story, prerequisites, examples, notation, pacing, and discussion questions.

In plain words
What is it for?
Use it after drafting a deck to review its narrative, explanations, worked examples, session continuity, and likely audience questions.
Why use it?
It exposes places where a presentation may be hard to follow or make assumptions the audience does not share.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is alohays/paper2pr's own configuration. It tells Claude Code how to work on paper2pr itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything paper2pr configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/deckprofile.py <Deck> # resolved profile JSON.

Reuse

Borrowing it

Nothing to install: this file belongs to alohays/paper2pr. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/alohays/paper2pr/main/.claude/agents/pedagogy-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/alohays/paper2pr

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 pedagogy-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/alohays/paper2pr/pedagogy-reviewer/github.svg)](https://agentmods.dev/agents/alohays/paper2pr/pedagogy-reviewer)
Your own site
<a href="https://agentmods.dev/agents/alohays/paper2pr/pedagogy-reviewer"><img src="https://agentmods.dev/badge/agents/alohays/paper2pr/pedagogy-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pedagogy-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/alohays/paper2pr/pedagogy-reviewer"><img src="https://agentmods.dev/badge/agents/alohays/paper2pr/pedagogy-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,247 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00057 $0.02247
Opus 5 $0.00028 $0.01123
Sonnet 5 $0.00011 $0.00449
Haiku 4.5 $0.00006 $0.00225

Measured 9d ago against content hash 40631567c188, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pedagogy-reviewer 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 9d 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/pedagogy-reviewer.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert pedagogy reviewer for presentation slides. You do not know who the audience is until the deck tells you; the first thing you do is find out, and every judgment after that is made for that audience, not a default one.

Step 0: load the deck's premises (always, before reading a slide)

python3 scripts/deckprofile.py <Deck>                          # resolved profile JSON
cat "$(python3 scripts/deckpath.py <Deck> --field config)"     # <deck>.deck.yml

From the profile JSON take: profile, duration_min, speaking_min, series_course, session_title, prior_session, sources. From <deck>.deck.yml take the audience block (assumes, description, size, prior) and delivery; when the deck has no audience block, use the audience: section of .claude/rules/slide-profiles/<profile>.yml for the profile the JSON names. If the deck has no deck.yml at all, say so in the report and review against the genre default profile.

Your report header states the audience you reviewed for, verbatim. A review that never says who it reviewed for is not checkable.

Your Task

Review the entire slide deck holistically. Produce a pedagogical report covering narrative arc, pacing, notation clarity, and audience preparation, then answer the devil's-advocate challenges below. Do NOT edit any files.

The prior-session callback

When the profile JSON has prior_session (the deck belongs to a series and is not the first session), the deck must open by connecting to that actual session - prior_session gives its title, date, week and presenter. Check that a slide near the top names where that session left off, and that the callback matches what that session was (a guest talk counts, and is called back as a guest talk). When prior_session is null, skip this check; do not invent a previous session.

13 Pedagogical Patterns to Validate

1. MOTIVATION BEFORE FORMALISM

  • Every new concept MUST start with "Why?" before "What?"
  • Pattern: Motivating slide -> Definition -> Worked example
  • Red flag: Formal definition appears without context or motivation

Read the full file on GitHub · 214 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. 9d ago First seen · 214 lines · 57 tokens per session scan A 40631567c188

Subscribe to this mod's changes

pedagogy-reviewer is an agent published in the GitHub repository alohays/paper2pr (6 stars, last pushed 7d ago), licensed MIT. It adds 57 tokens to every session and 2,247 once invoked, about $0.0003 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.

Related

Other agents, from other repositories