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 math-paper-huaweigit 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/math-paper-huawei)<a href="https://agentmods.dev/skills/lkq667/metamath-harness/math-paper-huawei"><img src="https://agentmods.dev/badge/skills/lkq667/metamath-harness/math-paper-huawei/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/math-paper-huawei"><img src="https://agentmods.dev/badge/skills/lkq667/metamath-harness/math-paper-huawei.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 | $0.00067 | $0.07481 |
| Opus 5 | $0.00034 | $0.03741 |
| Sonnet 5 | $0.00013 | $0.01496 |
| Haiku 4.5 | $0.00007 | $0.00748 |
Grade A, and why
math-paper-huawei 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 11d 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.
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.
- AGENT.md 2.2 KB
- agents/openai.yaml 338 B
- assets/drawio/template_library.json 112 KB
- assets/drawio/UPSTREAM.md 1.4 KB
- assets/latex/runtime-manifest.json 618 B
- assets/latex/texlive.profile 648 B
- assets/reference-pictures/Chen_AerialMind_2026.jpg 424 KB
- assets/reference-pictures/Han_VideoEspresso_2025.jpg 869 KB
- assets/reference-pictures/Liu_Controllable_2025.jpg 249 KB
- assets/reference-pictures/Liu_EEG2Video_2024.jpg 296 KB
- assets/reference-pictures/Liu_SLAM_2024.jpg 368 KB
- assets/reference-pictures/Ni_ColNeRF_2024.jpg 243 KB
- assets/reference-pictures/屏幕截图 2026-05-29 223805.png 258 KB
- assets/reference-pictures/屏幕截图 2026-05-29 223853.png 279 KB
- assets/reference-pictures/屏幕截图 2026-05-30 203950.png 600 KB
- assets/templates/example.tex 12 KB
- assets/templates/figures/logo.pdf 320 KB
- assets/templates/figures/title.pdf 325 KB
- assets/templates/gmcm.bst 33 KB
- assets/templates/gmcmthesis.cls 21 KB
- assets/templates/main.tex 12 KB
- assets/templates/py-figures/causal_effects_line_template.py 3.0 KB runs code
- assets/templates/py-figures/dynamics_phase_portrait_template.py 708 B runs code
- assets/templates/py-figures/multi_panel_hero_support_template.py 1.8 KB runs code
- assets/templates/py-figures/network_curvature_multiscale_template.py 2.0 KB runs code
- assets/templates/py-figures/network_resilience_template.py 1.4 KB runs code
- assets/templates/py-figures/optimization_convergence_template.py 1.2 KB runs code
- assets/templates/py-figures/optimization_pareto_template.py 963 B runs code
- assets/templates/py-figures/sensitivity_sobol_heatmap_template.py 997 B runs code
- assets/templates/py-figures/sensitivity_tornado_template.py 874 B runs code
- assets/templates/py-figures/spatial_contour_flow_template.py 725 B runs code
- assets/templates/py-figures/spatiotemporal_chronological_network_template.py 2.3 KB runs code
- assets/templates/py-figures/stats_interval_lollipop_template.py 1.2 KB runs code
- assets/templates/py-figures/temporal_bursty_activity_template.py 1.2 KB runs code
- assets/templates/py-figures/trend_confidence_template.py 1.3 KB runs code
- mathmodel-card.yml 3.2 KB
- README.md 4.2 KB
- references/appendix-code-prose-style.md 2.9 KB
- references/auto-checklist.md 18 KB
- references/drawing-pipeline.md 5.0 KB
- references/latex-bootstrap.md 1.9 KB
- references/literature.md 1.4 KB
- references/model-writing-b477.md 2.0 KB
- references/problem-statements/2023-A-WLAN网络信道接入机制建模.pdf 1498 KB
- references/py-chart-selection.md 3.2 KB
- references/py-palette-export.md 3.7 KB
- references/py-template-recipes.md 2.9 KB
- references/visual-style.md 7.5 KB
- references/workflow.md 19 KB
- scripts/checks/ai_prompt_common.py 3.5 KB runs code
- scripts/checks/check_abstract_no_formula.py 1.7 KB runs code
- scripts/checks/check_abstract_one_page.py 6.6 KB runs code
- scripts/checks/check_ai_prompt_paths.py 5.2 KB runs code
- scripts/checks/check_appendix_code_cleanliness.py 6.6 KB runs code
- scripts/checks/check_appendix_code_equivalence.py 1.4 KB runs code
- scripts/checks/check_bibliography_sources.py 1.3 KB runs code
- scripts/checks/check_body_page_count_minimum.py 3.1 KB runs code
- scripts/checks/check_code_distribution.py 2.4 KB runs code
- scripts/checks/check_data_sources.py 3.9 KB runs code
- scripts/checks/check_deliverable_scorecard.py 1.3 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.
- 11d ago First seen · 144 lines · 67 tokens per session scan A 83a93a39463b
math-paper-huawei is a skill published in the GitHub repository LKQ667/metamath-harness (15 stars, last pushed yesterday), with no licence file. It adds 67 tokens to every session and 7,481 once invoked, about $0.0003 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.
Other skills, from other repositories
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
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
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
nature-experiment-log
A workflow for turning experiment notes, images, audio, or text into structured Markdown laboratory logs with YAML metadata. It can also organize raw attachments and optionally connect the logs to Feishu or Obsidian.
parsing-ccda-documents
Parses C-CDA / CCD XML clinical documents to extract human-readable section narrative plus coded entries, keyed by section LOINC codes and templateIds. Use before OpenMed processing when ingesting C-CDA R2.1 documents (CCD, Discharge Summary, H&P, Consultation Note) exported from an EHR and you need the narrative…
structuring-radiology-reports
Converts free-text radiology narratives into structured findings and impression — with measurements, laterality, anatomy, and follow-up recommendations — after OpenMed NER. Use when the user has a CT/MRI/X-ray/ultrasound/mammography report and needs the sections split (technique, comparison, findings, impression)…