A multi-agent workflow that turns a scientific paper from arXiv, a repository of research papers, into executable and reproducible code, notebooks, and result comparisons.

Use it to implement or reproduce an arXiv paper, create a working repository and Jupyter notebook, and compare new results with the paper.

It organizes the work into stages so the paper's methods can be interpreted, implemented, run, and compared with reported results. Reproducible means someone else can repeat the process and obtain comparable outputs.

arxivist — Skill for Claude Code and Codex by qosi-org

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.

Any agent

npx skills add qosi-org/arxivist --skill skill

Clone the repo

git clone --depth 1 https://github.com/qosi-org/arxivist

Made for: Claude Code, Codex.

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/skills/qosi-org/arxivist/skill/github.svg)](https://agentmods.dev/skills/qosi-org/arxivist/skill)

Your own site

<a href="https://agentmods.dev/skills/qosi-org/arxivist/skill"><img src="https://agentmods.dev/badge/skills/qosi-org/arxivist/skill/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/skills/qosi-org/arxivist/skill"><img src="https://agentmods.dev/badge/skills/qosi-org/arxivist/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 178 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,203 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00178	$0.02203
Opus 5.5	$0.00071	$0.00881
Sonnet 5.5	$0.00036	$0.00441
Haiku 4.5	$0.00018	$0.00220

Measured 2mo ago against content hash 2792febc9129, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arxivist 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 2mo 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.

skill/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ArXivist — Multi-Agent Research-to-Code Orchestrator

You are the ArXivist Orchestrator. Your role is to coordinate a pipeline of 6 specialist sub-agents that transform a scientific paper into a fully reproducible, executable codebase.

You do NOT execute any stage yourself. You load each sub-agent's instructions at the right moment, validate their outputs, manage pipeline state, and advance the workflow.

Quick Reference: Sub-Agent Roster

Stage	File	Role	Input	Output
1	`agents/01_paper_parser.md`	PDF → SIR	Paper PDF/URL	SIR artifact
2	`agents/02_sir_registry.md`	SIR storage & retrieval	SIR artifact	Registry entry
3	`agents/03_architecture_planner.md`	SIR → Architecture Plan	SIR	Arch plan
4	`agents/04_code_generator.md`	Arch Plan → Full Repo	Arch plan + SIR	Git repo
5	`agents/05_notebook_generator.md`	Repo → .ipynb	Repo structure	Jupyter notebook
6	`agents/06_results_comparator.md`	Results → Comparison Report	User results + SIR	Comparison artifacts

Master Filesystem Layout

arxivist-workspace/
├── sir-registry/                    ← Global SIR registry (one folder per paper)
│   └── {paper_id}/
│       ├── sir.json                 ← Full SIR artifact
│       ├── metadata.json            ← Paper metadata + provenance
│       └── pipeline_state.json      ← Current pipeline state for this paper
│
└── paper-repos/                     ← Generated paper repositories
    └── {paper_id}/
        ├── src/                     ← Source code
        ├── configs/                 ← Config files
        ├── docker/                  ← Dockerfile + runtime setup
        ├── data/                    ← Dataset download scripts
        ├── notebooks/               ← Jupyter notebooks (.ipynb)
        ├── results/                 ← User-supplied experiment results
        ├── comparison/              ← Comparison artifacts (Stage 6 output)
        │   ├── benchmark_comparison.md
        │   ├── reproducibility_score.json
        │   ├── hallucination_report.md
        │   └── verification_log.md
        └── README.md

Read the full file on GitHub · 222 lines

Files

What ships with it

13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 222 lines · 178 tokens per session scan A 2792febc9129

Subscribe to this mod's changes

arxivist is a skill published in the GitHub repository qosi-org/arxivist (19 stars, last pushed 13d ago), licensed MIT. It adds 178 tokens to every session and 2,203 once invoked, about $0.0007 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.

Building agents Research Scientific ai-agents arxiv reproducibility reproducible-research

arxivist next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
arxivistqosi-org/arxivist	Skill	19	13d ago	MIT	A	178	Claude Code, Codex
check-questionscalkit/calkit	Skill	61	yesterday	MIT	A	51	Claude Code
build-paper-pipelinecalkit/calkit	Skill	61	yesterday	MIT	A	0	Claude Code
connect-overleaf-projectcalkit/calkit	Skill	61	yesterday	MIT	A	101	Claude Code
figure-styleaipoch/open-science	Skill	5.5k	yesterday	Apache-2.0	A	91	Claude Code, Codex
remote-compute-sshaipoch/open-science	Skill	5.5k	yesterday	Apache-2.0	A	53	Claude Code, Codex
literature-reviewaipoch/open-science	Skill	5.5k	yesterday	Apache-2.0	A	54	Claude Code, Codex