screen-papers

screen-papers is a command for Claude Code from TobiasBlask/open-paper-machine. It costs 60 tokens per session (427 once invoked), scanned A, original, MIT.

A structured workflow for screening research papers for a systematic literature review, which is a documented method for finding and selecting studies. It applies inclusion, exclusion, and quality checks and records the results.

In plain words
What is it for?
It helps screen titles, abstracts, and full papers, assess study quality, create a PRISMA flow diagram, and update the research database.
Why use it?
It makes paper selection consistent and auditable instead of relying on undocumented personal judgment.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the open-academic-paper-machine plugin — 33 skills, 21 commands, 4 agents 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/tobiasblask/open-paper-machine/screen-papers
Clone the repo
git clone --depth 1 https://github.com/TobiasBlask/open-paper-machine

Made for: Claude Code.

Or install open-academic-paper-machine, the plugin that ships this one along with the rest of its 33 skills, 21 commands, 4 agents.

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 screen-papers

README.md
[![agentmods](https://agentmods.dev/badge/commands/tobiasblask/open-paper-machine/screen-papers.svg)](https://agentmods.dev/commands/tobiasblask/open-paper-machine/screen-papers)
Your own site
<a href="https://agentmods.dev/commands/tobiasblask/open-paper-machine/screen-papers"><img src="https://agentmods.dev/badge/commands/tobiasblask/open-paper-machine/screen-papers.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 427 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 5.1 $0.00060 $0.00427
Opus 5 $0.00030 $0.00214
Sonnet 5 $0.00012 $0.00085
Haiku 4.5 $0.00006 $0.00043

Measured 6d ago against content hash 8e1453ad22f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

screen-papers 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.

commands/screen-papers.md · 39 lines

What it actually says

Screen Papers: $ARGUMENTS

Activate the screening-engine skill. Read skills/screening-engine/SKILL.md in full.

Execute the complete 6-step screening workflow:

  1. DEFINE inclusion/exclusion criteria (present for approval before screening)
  2. SCREEN title/abstract for all papers in literature_base.csv
  3. SCREEN full-text for included and uncertain papers
  4. ASSESS quality of included papers (Q1-Q8 checklist)
  5. GENERATE PRISMA flow diagram (text + visual via figure-engine)
  6. SAVE all screening artifacts and update literature_base_screened.csv

Input

$ARGUMENTS can be:

  • Empty — screens all papers in literature_base.csv using default criteria
  • File path to a specific CSV (e.g., @literature_base_v2.csv)
  • Criteria description (e.g., "only empirical papers 2020-2025 in enterprise context")
  • "resume" — continue a previously started screening session

Output

  • screening/screening_protocol.md — documented criteria and process
  • screening/title_abstract_screening.csv — all T/A screening decisions with reasons
  • screening/full_text_screening.csv — full-text screening decisions
  • screening/quality_assessment.csv — quality scores for included papers
  • screening/screening_summary.md — PRISMA counts and summary statistics
  • literature_base_screened.csv — final set of included papers
  • figures/fig_prisma_flow.png — visual PRISMA diagram
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. 6d ago First seen · 39 lines · 60 tokens per session scan A 8e1453ad22f5

Subscribe to this mod's changes

screen-papers is a command published in the GitHub repository TobiasBlask/open-paper-machine (18 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 427 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 2026-08-30.