What is reviewer AGENTS.md?

Instructions for a reproducible system that uses several software agents to review academic economics papers. It processes research PDFs, assigns reviewers, validates their structured results, and combines them for editing.

Use it to preprocess papers, check parser quality, choose reviewers, run reviews, validate JSON results, remove duplicate findings, and prepare material for an editor.

It defines where each paper artifact belongs and which checks happen before review, reducing confusion and inconsistent results across review runs. It also records reviewer selection and output validation for later inspection.

How Ingar30/reviewer configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Ingar30/reviewer. 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/Ingar30/reviewer/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Ingar30/reviewer

Made for: Codex, OpenCode.

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/instructions/ingar30/reviewer/agents-md/github.svg)](https://agentmods.dev/instructions/ingar30/reviewer/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ingar30/reviewer/agents-md"><img src="https://agentmods.dev/badge/instructions/ingar30/reviewer/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ingar30/reviewer/agents-md"><img src="https://agentmods.dev/badge/instructions/ingar30/reviewer/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,468 This file is loaded in full into every session.

When invoked 1,468 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01468	$0.01468
Opus 5.5	$0.00587	$0.00587
Sonnet 5.5	$0.00294	$0.00294
Haiku 4.5	$0.00147	$0.00147

Measured 14d ago against content hash 493078b376ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reviewer AGENTS.md 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 14d 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.

AGENTS.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project purpose

This repository builds and runs a reproducible multi-agent reviewer for academic economics papers.

The normal workflow is:

Put source PDFs in inputs/.
Preprocess each paper into structured artifacts under work/<paper_id>/parsed/.
Render run-specific prompts under work/<paper_id>/prompts/.
Run parser-quality preflight before substantive review.
Route substantive reviewers around parser-quality warnings using deterministic artifacts.
Run the single conservative applicability router. The 8 universal review-stage auditors always run; conditional specialists are skipped only when their entire remit is clearly absent. Mixed, unknown, or lower-confidence classifications expand to every conditional specialist.
Store applicability provenance and the active reviewer roster under work/<paper_id>/selection/.
Rerender prompts for the selected reviewer roster with parser-quality guidance.
Run the selected reviewer agents on the parsed artifacts.
Store and validate reviewer JSON outputs under work/<paper_id>/reviews/.
Conservatively normalize reviewer outputs into a precision-first, lossless editor bundle that preserves every source finding's details and avoids merging distinct concerns.
Build editor input from a deterministic brief, the lossless normalized bundle, and a compact provenance index for the validated reviewer JSON files. Do not duplicate raw reviewer JSON or truncate evidence.
Run the editor to author structured editorial decisions/prose, then validate and deterministically render the final Markdown under outputs/<paper_id>/report.md.
Smoke-check the final report.

Canonical file locations

Source PDFs: inputs/
Parsed artifacts: work/<paper_id>/parsed/
Reviewer outputs: work/<paper_id>/reviews/
Reviewer selection: work/<paper_id>/selection/
Final reports: outputs/<paper_id>/

Path conventions

If the user refers to a bare source PDF filename, first resolve it under inputs/.
Prefer project-relative paths over absolute paths when possible.
Do not assume a file is outside the repo unless the user explicitly says so.

Read the full file on GitHub · 74 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.

14d ago Changed · +23 tokens per session 493078b376ff
1mo ago Changed · +62 tokens per session f2dd2f199872
1mo ago Changed · +1 lines · +78 tokens per session 4b16e66e1ab0
1mo ago Changed · +81 tokens per session 702e0e15b7c3
1mo ago Changed · +7 lines · +185 tokens per session 16a50c9e7cf0
2mo ago Changed · +1 lines · +187 tokens per session 2497229e96f8
2mo ago First seen · 65 lines · 852 tokens per session scan A 46a9b6700a4a

Subscribe to this mod's changes

reviewer AGENTS.md is an instructions file published in the GitHub repository Ingar30/reviewer (230 stars, last pushed 8d ago), licensed MIT. It adds 1,468 tokens to every session, about $0.0059 per session on Opus 5.5. 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.

Research codex economics paper-review research-tools

reviewer AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
reviewer AGENTS.mdIngar30/reviewer	Instructions file	230	8d ago	MIT	A	1,468	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

reviewer: Instructions file for Codex