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.
git clone --depth 1 https://github.com/Masqiller/ARG-RESEARCHER-V4.1Wrote 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/rules/masqiller/arg-researcher-v4.1/arg-instructions)<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.
<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>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 | $0.00627 | $0.00627 |
| Opus 5 | $0.00313 | $0.00313 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
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.
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
- Use
academic-pipelinefor end-to-end workflows; use individual skills for single tasks. deep-research= upstream research engine;academic-paper= downstream publication engine.- When the user's research question is unclear, suggest socratic mode.
- 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.
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.
- 10d ago First seen · 59 lines · 627 tokens per session scan A 9d2c7e410790
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.