physics

physics is a skill for Claude Code from Rockielab/rockie-claude. It costs 75 tokens per session (2,028 once invoked), scanned A, original, Apache-2.0.

A routing guide for physics research requests involving simulations, calculations, models, validation, or scientific computing. It directs requests to areas such as molecular dynamics, plasma physics, radiation, and cosmology.

In plain words
What is it for?
Use it to classify physics work, select an open-source-first simulation path, prepare inputs, and route execution or result-interpretation requests to the responsible workflow.
Why use it?
It helps choose an appropriate physics method and tool when a request spans several specialized fields or when the right approach is unclear.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the rockie-claude plugin — 29 skills, 1 MCP server shipped together

Good fit Use it to classify physics work, select an open-source-first simulation path, prepare inputs, and route execution or result-interpretation requests to the responsible workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rockielab/rockie-claude/physics
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 Rockielab/rockie-claude --skill physics
Clone the repo
git clone --depth 1 https://github.com/Rockielab/rockie-claude

Made for: Claude Code.

Or install rockie-claude, the plugin that ships this one along with the rest of its 29 skills, 1 MCP server.

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 physics

README.md
[![agentmods](https://agentmods.dev/badge/skills/rockielab/rockie-claude/physics/github.svg)](https://agentmods.dev/skills/rockielab/rockie-claude/physics)
Your own site
<a href="https://agentmods.dev/skills/rockielab/rockie-claude/physics"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/physics/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 physics

Your own site · 80×15
<a href="https://agentmods.dev/skills/rockielab/rockie-claude/physics"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/physics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,028 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 $0.00075 $0.02028
Opus 5 $0.00037 $0.01014
Sonnet 5 $0.00015 $0.00406
Haiku 4.5 $0.00007 $0.00203

Measured 9d ago against content hash 2cc6c2443800, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

physics 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.

The scan reads SKILL.md. This mod also ships 7 executable files (runtime/classifier/classify_prompt.py, runtime/parse_physics_log.py, templates/astro-cosmology/athena-handoff/run_handoff.sh, …), 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • physics — 100% identical, 0 lines differ
project-harness/skills/physics/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Physics Research Router

Use this top-level skill for physics requests that imply simulation, calculation, modeling, validation, input-deck generation, run monitoring, or result interpretation. Current skill discovery is top-level only, so the domain modules are routed references under references/ rather than nested discoverable skills.

Physics is a router by default, not a direct provisioner. If a user asks for direct monitor status without a bound underlying run owner, return router_not_provisioner. Executed-run monitoring belongs to the owning provisioner parent skill such as experiment or inference-engineer, not the physics router itself.

First Steps

  1. Classify the request into one family: force_fields, molecular_dynamics, electronic_structure, particle_transport_collision, continuum_multiphysics, plasma_pic, nuclear_radiation, astro_cosmology, or literature_only.
  2. If classification is ambiguous and the answer would materially change the engine or safety posture, ask at most two clarifying questions. If the user does not answer, choose the safest open-source-first default and state the assumption.
  3. Load the routed reference module plus references/licensing.md and references/software-landscape.md.
  4. Write a run plan before execution or handoff.
  5. Attach the matching dashboard profile id and preserve every generated config, script, log, parser output, artifact path, and Note outline.

Non-computational literature review requests route to source search and note writing only. Do not invent a simulation run.

Router Rules

Signal Family Reference
Missing parameters, charges, water/ion compatibility, metals, surfaces, unusual residues, mixing rules force_fields references/force-fields.md
Classical atomistic dynamics, LAMMPS/GROMACS/OpenMM, trajectory, thermostat, barostat, enhanced sampling molecular_dynamics references/molecular-dynamics.md
DFT, SCF, band structure, orbitals, phonons, geometry optimization, AIMD setup electronic_structure references/electronic-structure.md
Detector simulation, event generation, collisions, PYTHIA, MadGraph, Geant4, ROOT particle_transport_collision references/particle-transport-collision.md
CFD, FEA, mesh, residuals, CFL, stress, heat transfer, coupled PDEs, OpenFOAM, SU2, MOOSE, CalculiX continuum_multiphysics references/continuum-multiphysics.md
Plasma sheath, PIC, fields plus particles, WarpX, Smilei, openPMD, Courant constraints plasma_pic references/plasma-pic.md
Neutron/photon transport, reactor, shielding, tallies, depletion, source convergence, OpenMC, MCNP nuclear_radiation references/nuclear-radiation.md
Galaxy, cosmology, N-body, MHD, redshift, Athena++, GADGET-family workflows astro_cosmology references/astro-cosmology.md
Literature review, compare papers, summarize methods without running literature_only source search and note writing

Read the full file on GitHub · 188 lines

Files

What ships with it

55 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.

  1. 9d ago First seen · 188 lines · 75 tokens per session scan A 2cc6c2443800

Subscribe to this mod's changes

physics is a skill published in the GitHub repository Rockielab/rockie-claude (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 2,028 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

autoresearch

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…

Orchestra-Research/AI-Research-SKILLs · 98 tokens

release-doi

A release procedure for research repositories that publish versions with a DOI, a permanent identifier for scholarly work, through Zenodo.

shimo4228/claude-harness · 126 tokens

content-refinement-agent

Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devil's Advocate…

Ar9av/PaperOrchestra · 145 tokens

section-writing-agent

Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimentallog.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges…

Ar9av/PaperOrchestra · 125 tokens

plotting-agent

Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimentallog.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER…

Ar9av/PaperOrchestra · 102 tokens

outline-agent

Step 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimentallog.md, template.tex, conferenceguidelines.md) into a strict JSON outline containing a plotting plan, literature search plan (Intro + Related Work), and section-level writing plan with citation hints. TRIGGER when the orchestrator…

Ar9av/PaperOrchestra · 99 tokens