hep-workflow: Skill for Claude Code

.agents/skills/hep-paper-formalize/SKILL.md

hep-paper-formalize is a skill for Claude Code, Codex from huangzhonglv/hep-workflow. It costs 142 tokens per session (4,859 once invoked), scanned A, original, MIT.

A workflow for reading a research paper from arXiv, a public science-paper repository, a DOI, or a local PDF and turning it into structured files for reproduction. Reproduction means rebuilding a paper's setup or calculations to compare results.

In plain words
What is it for?
It helps prepare paper metadata, extracted content, reproduction targets, model definitions, constraints, calculation tasks, and benchmark values for high-energy physics research.
Why use it?
It separates information taken from the paper from the later model and calculation work, reducing the risk of treating published formulas or results as the computational implementation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; installed under .agents/ (shared by several agents).

This is huangzhonglv/hep-workflow's own configuration. It tells Claude Code and Codex how to work on hep-workflow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hep-workflow configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/init_foundation_attempt.py \.

Reuse

Borrowing it

Nothing to install: this file belongs to huangzhonglv/hep-workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/huangzhonglv/hep-workflow/main/.agents/skills/hep-paper-formalize/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/huangzhonglv/hep-workflow

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.

agentmods badge for hep-paper-formalize

README.md
[![agentmods](https://agentmods.dev/badge/skills/huangzhonglv/hep-workflow/hep-paper-formalize/github.svg)](https://agentmods.dev/skills/huangzhonglv/hep-workflow/hep-paper-formalize)
Your own site
<a href="https://agentmods.dev/skills/huangzhonglv/hep-workflow/hep-paper-formalize"><img src="https://agentmods.dev/badge/skills/huangzhonglv/hep-workflow/hep-paper-formalize/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 hep-paper-formalize

Your own site · 80×15
<a href="https://agentmods.dev/skills/huangzhonglv/hep-workflow/hep-paper-formalize"><img src="https://agentmods.dev/badge/skills/huangzhonglv/hep-workflow/hep-paper-formalize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,859 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00142 $0.04859
Opus 5 $0.00071 $0.02429
Sonnet 5 $0.00028 $0.00972
Haiku 4.5 $0.00014 $0.00486

Measured 11d ago against content hash 80eca5f67784, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hep-paper-formalize 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/init_paper_project_skeleton.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/hep-paper-formalize/SKILL.md · 374 lines

How it starts

The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HEP Paper Formalizer

Turn a published paper into the workspace artifacts needed for paper-anchored reproduction. This skill has two independent modes: Setup mode authors the literature/ inputs, and Formalize mode reads literature/paper-extract.json to author model/, constraints/, and model/benchmarks.json. Both modes write only private foundation candidates and require mechanical finalization before their outputs become authoritative.

This skill operates under docs/contracts/honest-reproduction-principle.md. Paper formulas, curves, tables, and benchmark numbers are comparison targets only. They must not become computational backends for Package-X, Python translation, scans, or reproduction verdicts.

Mode selection is normally made by repro-orchestrator from manifest.artifacts.model.status: a paper-first project runs Setup then Formalize; a project that already has a model can run Setup only; a project with existing literature/paper-extract.json can run Formalize only.

1. Mode Classification

Classify the mode before reading or writing artifacts.

Mode Inputs Use when First action Hard fails
setup-only Paper identifier or PDF path; project name or existing project directory Add literature/ artifacts to a project whose model already exists, or prepare comparison targets before later formalization Locate or initialize the skeleton, allocate a Setup candidate, then author the literature files Missing paper identifier; request to write calculation outputs; no user decision on target subset when target selection is ambiguous
formalize-only Existing literature/paper-extract.json; project directory Convert a completed paper extract into model/, constraints/, and benchmark artifacts Allocate a Formalize candidate, then read its seeded extract and author model/constraint files Missing paper extract; extracted formulas requested as calculation backend; request to fetch latest external constraints instead of using the paper
setup+formalize Paper identifier or PDF path; project name or empty project directory Build a paper-first workspace from scratch Run Setup mode through user target confirmation, then continue into Formalize mode Any Setup hard fail; user declines target set; unresolved canonical naming conflicts

Read the full file on GitHub · 374 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. 11d ago First seen · 374 lines · 142 tokens per session scan A 80eca5f67784

Subscribe to this mod's changes

hep-paper-formalize is a skill published in the GitHub repository huangzhonglv/hep-workflow (9 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 4,859 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

pydicom

Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.

K-Dense-AI/scientific-agent-skills · 56 tokens

pptx-posters

Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Use when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.

K-Dense-AI/scientific-agent-skills · 59 tokens

extracting-lab-tables

Detects and extracts tabular laboratory panels from PDFs, scans, and images into structured rows ready for OpenMed and FHIR. Use when the user has a CBC, CMP, lipid panel, or other lab report as a scanned image / PDF / spreadsheet and needs the test name, value, unit, reference range, and abnormal flag as clean rows.…

maziyarpanahi/openmed · 210 tokens

paper-spine

Build, rewrite, audit, submit, revise, or transfer scholarly papers end to end, producing verified LaTeX/PDF/Word and target-specific publication packages.

WUBING2023/PaperSpine · 37 tokens

paper-compile

A build workflow that turns LaTeX source files into a PDF and checks whether the paper compiles correctly. LaTeX is a text-based system commonly used for academic papers.

wanshuiyin/Auto-claude-code-research-in-sleep · 53 tokens

nsfc-budget

A tool that creates an editable LaTeX budget justification and renders it as a PDF for an NSFC research-funding application. NSFC is China’s National Natural Science Foundation, and a budget justification explains why proposed costs are needed.

huangwb8/ChineseResearchLaTeX · 138 tokens