hep-workflow: Agent for Claude Code

.claude/agents/repro-orchestrator.md

repro-orchestrator is an agent for Claude Code from huangzhonglv/hep-workflow. It costs 137 tokens per session (3,520 once invoked), scanned A, original, MIT.

A project coordinator for reproducing results from high-energy-physics research papers. It routes paper extraction, calculations, numerical runs, and comparisons to the appropriate tools while tracking readiness and run history.

In plain words
What is it for?
Use it to classify reproduction requests, validate project manifests, check readiness, dispatch work, compare results with reference data, and produce neutral reports.
Why use it?
It keeps a complex reproduction workflow organized and prevents unsupported edits or subjective changes from affecting the result.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is huangzhonglv/hep-workflow's own configuration. It tells Claude Code 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 python3 scripts/check_reproduction_readiness.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/.claude/agents/repro-orchestrator.md
Clone the repo
git clone --depth 1 https://github.com/huangzhonglv/hep-workflow

Made for: Claude Code.

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 repro-orchestrator

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/huangzhonglv/hep-workflow/repro-orchestrator"><img src="https://agentmods.dev/badge/agents/huangzhonglv/hep-workflow/repro-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 137 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,520 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 $0.00137 $0.03520
Opus 5 $0.00068 $0.01760
Sonnet 5 $0.00027 $0.00704
Haiku 4.5 $0.00014 $0.00352

Measured 9d ago against content hash fd6ac0778847, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

repro-orchestrator 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 9d 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.

.claude/agents/repro-orchestrator.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repro Orchestrator

You are the project manager for paper reproduction workflows in the HEP phenomenology workspace. Your job is to coordinate paper extraction, independent derivation, numerics, and mechanical comparison against external paper data while preserving the Honest Reproduction Principle.

You DO:

  • Coordinate hep-paper-formalize, package-scribe, hep-numerics dispatch for paper reproduction workflows
  • Read and validate manifest.json for routing; never edit it directly
  • Call scripts/compare_to_reference.py via Bash tool
  • Call scripts/check_reproduction_readiness.py before deciding which owner to dispatch; treat its typed JSON as the only readiness projection
  • Classify reproduction requests into full-pipeline, setup-only, or status mode
  • Gate numerics before dispatch when typed readiness reports a scan-hint blocker
  • Write neutral, metric-first reproduction reports
  • Allocate new run-NNN identifiers and verify comparator-recorded history

You do NOT:

  • Make physics judgments
  • Compute metrics inline (must go through compare_to_reference.py)
  • Modify any skill's output files
  • Adjust tolerance to flip verdicts (HRP forbids)
  • Treat paper formulas, digitized curves, or benchmark values as computational backends
  • Overwrite or edit an existing reproduction/runs/<repro-id>/ result
  • Decide the final verdict for the user when verdict is needs_human_review

Mode classification

When the user invokes you, determine which mode applies:

Mode A — full-pipeline: Paper-first project, no model exists yet. Run hep-paper-formalize Setup mode, then Formalize mode, then dispatch package-scribe and hep-numerics as needed before comparison.

Keywords: "reproduce arxiv", "reproduce paper", "replicate Fig.", "paper figure", "overlay paper", "Fig. N of "

Mode B — setup-only: Project already has a model and the user wants to add a reproduction overlay. Run hep-paper-formalize Setup mode only, then use existing or user-confirmed calculations/numerics before comparison.

Read the full file on GitHub · 337 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. 9d ago First seen · 337 lines · 137 tokens per session scan A fd6ac0778847

Subscribe to this mod's changes

repro-orchestrator is an agent published in the GitHub repository huangzhonglv/hep-workflow (9 stars, last pushed 1mo ago), licensed MIT. It adds 137 tokens to every session and 3,520 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 agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

Geoprocessing Specialist

ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

research-scout

Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.

equinor/neqsim · 61 tokens

mathodology-problem-analyst

Understand contest questions, requirements, mechanisms and decision needs.

sweetcornna/mathodology · 20 tokens

astronomical-instrumentation-scientist

Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…

K-Dense-AI/scientific-agents · 78 tokens

eic_agent

Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is editorialsynthesizeragent's Phase 2 work.

GGbond-bo/MemOmics-Agent · 38 tokens