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.
curl -O https://raw.githubusercontent.com/edwnh/dqmc/master/.claude/skills/dqmc-run/SKILL.mdgit clone --depth 1 https://github.com/edwnh/dqmcWrote 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/skills/edwnh/dqmc/dqmc-run)<a href="https://agentmods.dev/skills/edwnh/dqmc/dqmc-run"><img src="https://agentmods.dev/badge/skills/edwnh/dqmc/dqmc-run/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/skills/edwnh/dqmc/dqmc-run"><img src="https://agentmods.dev/badge/skills/edwnh/dqmc/dqmc-run.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 | $0.00042 | $0.00647 |
| Opus 5.5 | $0.00017 | $0.00259 |
| Sonnet 5.5 | $0.00008 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
dqmc-run 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Simulations
Inputs
- HDF5 simulation file(s) from the dqmc-generate and dqmc-parameter-scans skills
- Binary at
build/dqmc, worker utility fromdqmc-util worker
Outputs
- Updated HDF5 files with measurements in
/meas_eqlt/(and/meas_uneqlt/if enabled)
Decision Rules (single vs queue)
- Exactly 1 file: run it directly with
build/dqmc sim_0.h5. - 2+ files: use the queue/worker system (
dqmc-util enqueue+dqmc-util worker) even on a local workstation.- This avoids ad-hoc shell loops, makes restarts/checkpointing consistent, and scales to parallel execution safely.
Procedure
Single file:
build/dqmc sim_0.h5
With checkpointing (long runs):
build/dqmc -s 300 -t 3600 sim_0.h5 # checkpoint every 300 seconds, max runtime 3600 seconds
Multiple files (queue system):
# 1. Add files to queue/ (globs are expanded by Python, so quote them)
dqmc-util enqueue queue 'data/run/bin_*.h5'
# 2. Start workers
dqmc-util worker queue ./build/dqmc -n 8 -s 300 -t 3600 # 8 parallel workers
Multiple files (local temperature scan example):
# enqueue all bins across temperatures
dqmc-util enqueue queue 'runs/pi_pi_U8_6x6/T*/bin_*.h5'
# run N workers in parallel (pick N for your machine)
dqmc-util worker queue ./build/dqmc -n 8 -s 300 -t 3600
Validation (single file)
dqmc-util summary sim_0.h5
For multiple files:
dqmc-util print-n data/run/ # directory paths should end with '/'
Failure Modes
| Symptom | Cause | Recovery |
|---|---|---|
| "opening... failed" | File doesn't exist | Check path |
| NaN in output | Numerical instability | Reduce dt and/or n_matmul. Check parameters |
| Killed by scheduler | Exceeded time limit | Use -t flag, checkpoint enabled |
| Large errorbars | Sign problem | Add more sweeps and/or bins |
Do Not
- Kill running simulations without checkpointing (
-sflag) - Run multiple workers on the same file
- Use manual shell loops for 2+ files (prefer
dqmc-util enqueue+dqmc-util worker)
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.
- 2mo ago First seen · 77 lines · 42 tokens per session scan A ab61d85035dc
dqmc-run is a skill published in the GitHub repository edwnh/dqmc (19 stars, last pushed 7mo ago), licensed MIT. It adds 42 tokens to every session and 647 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.
dqmc-run compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dqmc-runedwnh/dqmc | Skill | 19 | 7mo ago | MIT | A | 42 | Claude Code |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |