agentmods.dev

dqmc: Skill for Claude Code

.claude/skills/dqmc-analyze/SKILL.md

dqmc-analyze is a skill for Claude Code from edwnh/dqmc. It costs 41 tokens per session (703 once invoked), scanned A, original, MIT.

A results-analysis tool for completed determinant quantum Monte Carlo (DQMC) simulations, a computer method for studying interacting particles. It calculates physical measurements with averages and standard errors.

In plain words
What is it for?
Use it to extract density, double occupancy, spin and density correlations, structure factors, Green’s functions, and pair susceptibilities from HDF5 simulation files.
Why use it?
It removes the need to manually combine simulation data and calculate uncertainty for each measurement.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is edwnh/dqmc's own configuration. It tells Claude Code how to work on dqmc 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 dqmc configures →

not rated 19repo 7mo ago A scan 41 tokens original MIT
View source ↗ edwnh/dqmc
Reuse

Borrowing it

Nothing to install: this file belongs to edwnh/dqmc. 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/edwnh/dqmc/master/.claude/skills/dqmc-analyze/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/edwnh/dqmc

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 dqmc-analyze

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/edwnh/dqmc/dqmc-analyze"><img src="https://agentmods.dev/badge/skills/edwnh/dqmc/dqmc-analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 703 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 $0.00041 $0.00703
Opus 5.5 $0.00016 $0.00281
Sonnet 5.5 $0.00008 $0.00141
Haiku 4.5 $0.00004 $0.00070

Measured 2mo ago against content hash 42f232bde815, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dqmc-analyze 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.

.claude/skills/dqmc-analyze/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Results

Inputs

  • Directory containing bin_*.h5 files (completed simulations)
  • Observable names (see table below)

Outputs

  • Dictionary with parameters and (mean, stderr) tuples for each observable

Procedure

Basic analysis:

from dqmc_util import analyze_hub

data = analyze_hub.get("data/run/", "sign", "den", "zzr")

print(f"sign = {data['sign'][0]:.4f} +/- {data['sign'][1]:.4f}")
print(f"density = {data['den'][0]:.4f} +/- {data['den'][1]:.4f}")

Available observables:

Name Description Requires
sign Fermion sign -
den Density -
docc Double occupancy <n_up n_down> -
gr, gk Green's function (real/k-space) -
nnr, nnq Density correlator / structure factor -
zzr, zzq Spin-z correlator / structure factor -
xxr Spin-x correlator -
swq0 S-wave pair structure factor -
nnrw0, zzrw0 Zero-freq susceptibilities period_uneqlt > 0
dwq0t D-wave pair susceptibility period_uneqlt > 0

Collect from multiple directories:

import os

def collect_results(base_dir, observables):
    results = []
    for subdir in sorted(os.listdir(base_dir)):
        path = os.path.join(base_dir, subdir)
        if os.path.isdir(path):
            try:
                results.append(analyze_hub.get(path + "/", *observables))
            except Exception as e:
                print(f"Skipping {path}: {e}")
    return results

Compute derived quantities:

# Magnetic moment squared from spin correlator
path = "data/run/"
data = analyze_hub.get(path, "zzr")
mz2 = 4 * data["zzr"][0][0, 0]       # [0] = mean, shape (Ny, Nx)
mz2_err = 4 * data["zzr"][1][0, 0]   # [1] = stderr

Validation

  • Errorbar on sign is significantly less than mean. Otherwise, sign problem is too severe.
  • Errorbars on observable are reasonable (not >> mean)

Failure Modes

Symptom Cause Recovery
KeyError for observable Observable not computed Check period_uneqlt setting
"No files found" Wrong path or no bin_*.h5 Verify directory structure
Large error bars Insufficient statistics Run more sweeps or bins

Read the full file on GitHub · 81 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. 2mo ago First seen · 81 lines · 41 tokens per session scan A 42f232bde815

Subscribe to this mod's changes

dqmc-analyze is a skill published in the GitHub repository edwnh/dqmc (19 stars, last pushed 7mo ago), licensed MIT. It adds 41 tokens to every session and 703 once invoked, about $0.0002 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 2026-09-01.

Analytics and metricsScientific
Related

dqmc-analyze compared with skills from other repositories

dqmc-analyze next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dqmc-analyzeedwnh/dqmcSkill197mo agoMITA41Claude Code
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35k2d agoApache-2.0A123Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA83Claude Code
matlabK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA44Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA71Claude Code, Codex
research-engineerdavila7/claude-code-templatesSkill33kyesterdayMITA43Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A205Claude Code