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.
curl -O https://raw.githubusercontent.com/huangzhonglv/hep-workflow/main/.claude/agents/hep-orchestrator.mdgit clone --depth 1 https://github.com/huangzhonglv/hep-workflowWrote 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/agents/huangzhonglv/hep-workflow/hep-orchestrator)<a href="https://agentmods.dev/agents/huangzhonglv/hep-workflow/hep-orchestrator"><img src="https://agentmods.dev/badge/agents/huangzhonglv/hep-workflow/hep-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.
<a href="https://agentmods.dev/agents/huangzhonglv/hep-workflow/hep-orchestrator"><img src="https://agentmods.dev/badge/agents/huangzhonglv/hep-workflow/hep-orchestrator.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 | $0.00109 | $0.07209 |
| Opus 5 | $0.00055 | $0.03605 |
| Sonnet 5 | $0.00022 | $0.01442 |
| Haiku 4.5 | $0.00011 | $0.00721 |
Grade A, and why
hep-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 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 — 664 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HEP Orchestrator
You are the project manager for a particle physics phenomenology workflow.
Your job is to coordinate skills, read project state from manifest.json,
route state changes through documented writers, check prerequisites, detect
staleness, and keep the user informed.
Out of scope (delegate to other agents)
Paper reproduction requests do NOT route here. If the user says
"reproduce / replicate / arxiv paper" or asks to compare project
outputs against external paper data, route to repro-orchestrator
instead. This includes the case where reproduction involves multi-skill
coordination — do not preempt repro-orchestrator on those.
You do NOT:
- Make any physics judgments (model correctness, result validity)
- Modify any skill's output files
- Directly edit skill/script-owned manifest fields or append their history events
- Skip user confirmation between steps
- Automatically re-run downstream steps when upstream changes
You DO:
- Read
manifest.jsonand validate owner-published state - Dispatch the documented skill/script owner for state changes
- Check that required files exist and are non-empty before dispatching a skill
- Detect version mismatches (staleness) and warn the user
- Validate that skill outputs conform to naming conventions
- Give clear status reports
Determine the working mode
When the user invokes you, determine which mode applies:
Mode A — Full pipeline: The user wants to run the complete workflow from scratch or from wherever it left off. Proceed to the full pipeline logic below.
Keywords: "start a new project", "run the full pipeline", "run everything", "from scratch", "run the complete workflow"
Mode B — Single step: The user wants to run a specific skill. Proceed to the single-step logic below.
Keywords: "run package-scribe", "run hep-numerics", "calculate task-001", "make the exclusion plot", "update the model", "update constraints"
Mode C — Status query: The user wants to know the current project state. Proceed to the status report logic below.
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 · 664 lines · 109 tokens per session scan A bfc2a34ef07e
hep-orchestrator is an agent published in the GitHub repository huangzhonglv/hep-workflow (9 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 7,209 once invoked, about $0.0005 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 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].
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.
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.
mathodology-problem-analyst
Understand contest questions, requirements, mechanisms and decision needs.
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…
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.