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.
npx skills add LKQ667/metamath-harness --skill modelviz-skillgit clone --depth 1 https://github.com/LKQ667/metamath-harnessWrote 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/lkq667/metamath-harness/modelviz-skill)<a href="https://agentmods.dev/skills/lkq667/metamath-harness/modelviz-skill"><img src="https://agentmods.dev/badge/skills/lkq667/metamath-harness/modelviz-skill/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/lkq667/metamath-harness/modelviz-skill"><img src="https://agentmods.dev/badge/skills/lkq667/metamath-harness/modelviz-skill.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 | $0.00164 | $0.03128 |
| Opus 5.5 | $0.00066 | $0.01251 |
| Sonnet 5.5 | $0.00033 | $0.00626 |
| Haiku 4.5 | $0.00016 | $0.00313 |
Grade A, and why
modelviz-skill scanned grade A with 1 finding 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 25d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`execute_plot_script` uses `subprocess.run([...], shell=False)`, passes the data path and output directory as arguments, sets `DATA_PATH` and `OUTPUT_DIR`, captures stdout/stderr, and records generated files. The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- .gitignore 279 B
- .ruff_cache/.gitignore 35 B
- .ruff_cache/0.16.6/10924813921752293158 236 B
- .ruff_cache/0.16.6/13333532810603305367 1.0 KB
- .ruff_cache/0.16.6/14907026519561136244 3.2 KB
- .ruff_cache/0.16.6/14999827074146728371 236 B
- .ruff_cache/0.16.6/1634992810150581693 284 B
- .ruff_cache/0.16.6/2312406069120860103 1.0 KB
- .ruff_cache/0.16.6/5829021234896270111 228 B
- .ruff_cache/0.16.6/6055657236328870016 3.2 KB
- .ruff_cache/CACHEDIR.TAG 43 B
- docs/assets/readme-preview-1.jpg 415 KB
- docs/assets/readme-preview-2.jpg 455 KB
- docs/assets/readme-preview-3.jpg 475 KB
- docs/evaluation_summary_for_interview.md 686 B
- docs/package_name_mapping.yaml 1.1 KB
- docs/requirement_vocabulary.yaml 12 KB
- docs/stage5_stage6_skill_workflow.md 1.5 KB
- docs/template_catalog.yaml 76 KB
- docs/template_index.csv 15 KB
- evals/__init__.py 49 B runs code
- evals/evaluation_cases.json 16 KB
- evals/evaluation_report.md 3.4 KB
- evals/evaluation_summary.json 19 KB
- evals/run_evaluation.py 37 KB runs code
- examples/requirement_test_cases.json 4.4 KB
- outputs/.gitkeep 0 B
- prompts/code_repair.md 232 B
- prompts/template_adaptation.md 319 B
- prompts/visual_quality_check.md 234 B
- README.md 24 KB
- requirements.txt 366 B
- ruff.toml 691 B
- schemas/__init__.py 356 B runs code
- schemas/requirement_schema.py 2.2 KB runs code
- src/__init__.py 56 B runs code
- src/prompts/__init__.py 1.2 KB runs code
- src/prompts/final_template_selector.py 2.1 KB runs code
- src/prompts/plot_code_repair.py 1.2 KB runs code
- src/prompts/requirement_parser.py 4.7 KB runs code
- src/prompts/template_adaptation_plan.py 1.2 KB runs code
- src/prompts/template_code_adapter.py 1.3 KB runs code
- src/prompts/visual_quality_checker.py 1.2 KB runs code
- src/schemas/__init__.py 3.2 KB runs code
- src/schemas/adaptation_plan.py 2.8 KB runs code
- src/schemas/adaptation_result.py 1.2 KB runs code
- src/schemas/candidate_template.py 3.9 KB runs code
- src/schemas/dataset_context.py 1.5 KB runs code
- src/schemas/dependency_report.py 4.2 KB runs code
- src/schemas/execution_result.py 924 B runs code
- src/schemas/final_template_selection.py 4.3 KB runs code
- src/schemas/repair_result.py 1.6 KB runs code
- src/schemas/technical_quality_report.py 1.5 KB runs code
- src/schemas/template_recommendation.py 5.0 KB runs code
- src/schemas/visual_quality_report.py 578 B runs code
- src/services/__init__.py 961 B runs code
- src/services/candidate_matching_pipeline.py 4.4 KB runs code
- src/services/final_template_selection_pipeline.py 9.8 KB runs code
- src/services/plot_quality_pipeline.py 13 KB runs code
- src/services/requirement_parser.py 6.1 KB runs code
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.
- 25d ago First seen · 331 lines · 164 tokens per session scan A 4f64357f8628
modelviz-skill is a skill published in the GitHub repository LKQ667/metamath-harness (22 stars, last pushed 22d ago), with no licence file. It adds 164 tokens to every session and 3,128 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
Other skills, from other repositories
translate-health-data
Turn raw health data into standardized data, and read a lab report without guessing. A lab report PDF, photo, spreadsheet or CSV becomes readings with LOINC codes and UCUM units; an Apple Health export becomes JSON lines; a symptom or diagnosis in any language becomes an ICPC-3 code; any reading becomes a FHIR…
faostat-analytical-brief
Use when the user wants a short, FAOSTAT-style analytical brief — a multi-page PDF policy document in the FAOSTAT house visual style, with a HIGHLIGHTS box, global/regional/country sections, numbered figures with source lines, explanatory notes, and a data appendix. Use when the user asks for "an analytical brief on…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
pydicom
Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
nature-paper-trans
A workflow for translating selected pages or a complete English research-paper PDF into a simplified-Chinese, image-based PDF. bioRxiv is not mentioned in the provided details; the workflow applies to research-paper PDFs generally.