arg-instructions

arg-instructions is a cursor rule for Cursor from Masqiller/ARG-RESEARCHER-V4.1. It costs 627 tokens per session, scanned A, original, MIT.

Instructions for an academic research assistant that supports research, paper writing, peer review, and workflow coordination. It includes modes for literature reviews, fact-checking, planning, revision, citations, and format conversion.

In plain words
What is it for?
Use it to plan or write papers, review methods, build literature reviews, check citations, prepare revision responses, and convert papers to LaTeX, DOCX, PDF, or Markdown.
Why use it?
It brings several academic writing tasks into one guided workflow. This can help organize evidence, drafts, reviews, and revisions in the right order.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to plan or write papers, review methods, build literature reviews, check citations, prepare revision responses, and convert papers to LaTeX, DOCX, PDF, or Markdown.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/masqiller/arg-researcher-v4.1/arg-instructions
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.

Clone the repo
git clone --depth 1 https://github.com/Masqiller/ARG-RESEARCHER-V4.1

Made for: Cursor.

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 arg-instructions

README.md
[![agentmods](https://agentmods.dev/badge/rules/masqiller/arg-researcher-v4.1/arg-instructions/github.svg)](https://agentmods.dev/rules/masqiller/arg-researcher-v4.1/arg-instructions)
Your own site
<a href="https://agentmods.dev/rules/masqiller/arg-researcher-v4.1/arg-instructions"><img src="https://agentmods.dev/badge/rules/masqiller/arg-researcher-v4.1/arg-instructions/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 arg-instructions

Your own site · 80×15
<a href="https://agentmods.dev/rules/masqiller/arg-researcher-v4.1/arg-instructions"><img src="https://agentmods.dev/badge/rules/masqiller/arg-researcher-v4.1/arg-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 627 This file is loaded in full into every session.
When invoked 627 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00627 $0.00627
Opus 5 $0.00313 $0.00313
Sonnet 5 $0.00125 $0.00125
Haiku 4.5 $0.00063 $0.00063

Measured 10d ago against content hash 9d2c7e410790, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

arg-instructions 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 10d 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.

.cursor/rules/arg-instructions.mdc · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Academic Research Graphify (ARG)

You are operating in the ARG repository — a suite of AI skills for rigorous academic research.

Skills & Modes

  • deep-research (7 modes): full, quick, socratic, review, lit-review, fact-check, systematic-review
  • academic-paper (10 modes): full, plan, outline-only, revision, revision-coach, abstract-only, lit-review, format-convert, citation-check, disclosure
  • academic-paper-reviewer (6 modes): full, re-review, quick, methodology-focus, guided, calibration
  • academic-pipeline (1 orchestrator): coordinates all above in a 10-stage workflow

Slash Commands

Command Description
/arg-full Full pipeline: research → write → review → revise → finalize
/arg-plan Socratic chapter-by-chapter planning
/arg-outline Detailed outline + evidence map
/arg-abstract Bilingual abstract (zh-TW + EN) + keywords
/arg-revision Revised draft + R&R responses
/arg-revision-coach Revision Roadmap + Response Letter skeleton
/arg-lit-review Annotated bibliography in paper format
/arg-format-convert Convert to LaTeX / DOCX / PDF / Markdown
/arg-citation-check Citation error report
/arg-disclosure Venue-specific AI-usage statement

When any of these commands are mentioned by the user, read the corresponding skill's SKILL.md file and MODE_REGISTRY.md for full details, then execute accordingly.

Routing Rules

  1. Use academic-pipeline for end-to-end workflows; use individual skills for single tasks.
  2. deep-research = upstream research engine; academic-paper = downstream publication engine.
  3. When the user's research question is unclear, suggest socratic mode.
  4. When the user wants to plan a paper, suggest plan mode.

Key Rules

  • All claims must have citations.
  • Evidence hierarchy: meta-analyses > RCTs > cohort > case reports > expert opinion.
  • Contradictions disclosed with evidence quality comparison.
  • AI disclosure in all reports.
  • Default output language matches user input.

Read the full file on GitHub · 59 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. 10d ago First seen · 59 lines · 627 tokens per session scan A 9d2c7e410790

Subscribe to this mod's changes

arg-instructions is a cursor rule published in the GitHub repository Masqiller/ARG-RESEARCHER-V4.1 (6 stars, last pushed 3mo ago), licensed MIT. It adds 627 tokens to every session, about $0.0031 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.