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.
npx agentmods add instructions/filipposcaramuzza/agentic-reviewer/agents-mdgit clone --depth 1 https://github.com/FilippoScaramuzza/agentic-reviewerWrote 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.
[](https://agentmods.dev/instructions/filipposcaramuzza/agentic-reviewer/agents-md)<a href="https://agentmods.dev/instructions/filipposcaramuzza/agentic-reviewer/agents-md"><img src="https://agentmods.dev/badge/instructions/filipposcaramuzza/agentic-reviewer/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01493 | $0.01493 |
| Opus 5 | $0.00746 | $0.00746 |
| Sonnet 5 | $0.00299 | $0.00299 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
agentic-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 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Reviewer — Journal Paper Review Framework
Project Overview
An OpenCode- and Codex-compatible agentic framework for academic paper peer review. Given a paper and a target journal/conference, a team of agents:
- Converts non-Markdown papers (PDF, DOCX, etc.) to Markdown using markitdown
- Explores the journal's requirements, recent publications, style guide, and reputation
- Reviews the paper against those requirements across five dimensions
- Compiles a final structured review report with ratings and recommendation
Every review session produces a timestamped report directory containing all artifacts.
Directory Structure
papers/— Place paper files here (PDF, DOCX, Markdown, etc.)context/<journal-slug>/— Cached exploration results per journal (auto-generated)scope-and-criteria.mdrecent-papers-analysis.mdstyle-guide.mdreputation-profile.mdrecent-papers/— Downloaded full-text papers (auto-generated at runtime)<slugified-title>.pdf— Downloaded paper PDFs<slugified-title>.md— Markitdown-converted versions
reports/<journal-slug>/<YYYY-MM-DD-HHMMSS>/— Timestamped report directory (auto-generated)00-session-info.md— Session metadata (journal, paper, date, timestamp)01-scope-and-criteria.md— Journal scope analysis02-recent-papers-analysis.md— Recent papers analysis03-style-guide.md— Style guide extraction04-reputation-profile.md— Reputation profile05-scope-review.md— Scope review06-methodology-review.md— Methodology review07-writing-style-review.md— Writing & style review08-statistics-review.md— Statistics review09-ethics-review.md— Ethics review10-final-review-report.md— Compiled final report (Markdown)10-final-review-report.pdf— Compiled final report (PDF, generated via pandoc)
.agents/skills/review-paper/— Shared workflow entrypoint.codex/agents/— Codex custom agent definitions matching the review roles
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.
- 6d ago First seen · 103 lines · 1,493 tokens per session scan A cf9f8a315c1b
agentic-reviewer AGENTS.md is an instructions file published in the GitHub repository FilippoScaramuzza/agentic-reviewer (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,493 tokens to every session, about $0.0075 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.
Other instructions, from other repositories
docsift CLAUDE.md
Instructions for anishmoncivarghese/docsift, covering docsift, key documents (read before making product decisions), commands, architecture (src layout, package docsift) and hard rules.
markitdown-for-ai AGENTS.md
Instructions for OpenTechIL/markitdown-for-ai, covering agents.md, project overview, conventional commits, types and examples.
pdfmux CLAUDE.md
Claude Code instructions for NameetP/pdfmux, covering pdfmux — agent instructions, project, commands, python and site.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).
phd-deepread-workflow CLAUDE.md
Instructions for heleninsights-dot/phd-deepread-workflow, covering claude.md, commands, install, test and code quality.
llm-wiki AGENTS.md
Instructions for cobusgreyling/llm-wiki, covering llm wiki agent instructions, architecture, page types, special files and log entry format.