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 ConmuYan/my-academic-skills --skill graph-fraudgit clone --depth 1 https://github.com/ConmuYan/my-academic-skillsWrote 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/conmuyan/my-academic-skills/graph-fraud)<a href="https://agentmods.dev/skills/conmuyan/my-academic-skills/graph-fraud"><img src="https://agentmods.dev/badge/skills/conmuyan/my-academic-skills/graph-fraud/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/conmuyan/my-academic-skills/graph-fraud"><img src="https://agentmods.dev/badge/skills/conmuyan/my-academic-skills/graph-fraud.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 | $0.00139 | $0.01876 |
| Opus 5 | $0.00069 | $0.00938 |
| Sonnet 5 | $0.00028 | $0.00375 |
| Haiku 4.5 | $0.00014 | $0.00188 |
Grade A, and why
graph-fraud 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 12d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graph fraud protocol (BWGNN)
Align the current repo to the field-default GFD setup from BWGNN
(squareRoot3/Rethinking-Anomaly-Detection). Numbers and loaders live in
references/bwgnn-protocol.md. Read it
before editing.
random_state=2 is the split seed, not model init.
--run 10 is 10 re-inits on that fixed split.
Do not implement “10 different splits”.
When to use
- Check
dataset.py/data.py/ configs against YelpChi, Amazon, T-Finance, T-Social - Add or fix abundant (40%) / scarce (1%, T-Social 0.01%) splits
- Add BWGNN-style
--run 10mean±std - User says 对齐 BWGNN / GFD 通用设置 / 10 seeds
When not to use
| Request | Do this instead |
|---|---|
Align to GADBench precomputed train_masks |
Follow GADBench; do not rewrite to random_state=2 |
| CARE-GNN 40/60 no-val split | Only if the user names CARE-GNN |
| Invent a new dataset protocol | Stop; this skill only standardizes the four GFD datasets |
Modes
| User signal | Mode |
|---|---|
| 检查 / audit / 是否符合 | audit |
| 对齐 / 改数据 / 配 10-run / 修 dataset.py | fix (default if they want the repo usable) |
audit does not write files. fix patches the smallest data/train entry points and re-audits.
Workflow
1. Locate
Find, do not assume names:
- Loaders:
dataset.py,data.py,data_loader.py,DataHelper/ - Entry:
train.py,main.py,run_*.py - Configs:
configs/*.yaml,config/*.yml - Data:
YelpChi.mat,Amazon.mat, DGL binaries namedtfinance/tsocial
Run scripts/audit_gfd_protocol.py from this skill directory (the folder that contains this SKILL.md):
python scripts/audit_gfd_protocol.py <repo-root>
Then read the hit files. The script only finds markers; you judge the code.
2. Audit (required in both modes)
Check every box against references/bwgnn-protocol.md.
A failed box in fix mode is a patch target.
[ ] Amazon eligible starts at 3305; those nodes never enter train/val/test
[ ] Yelp / T-Finance / T-Social use all labeled nodes
[ ] T-Finance labels go through argmax(1) when loaded from DGL
[ ] T-Finance / T-Social use load_graphs, not .mat
[ ] Split is stratified train_test_split, random_state=2 both times
[ ] Remainder uses test_size=0.67 (val:test ≈ 1:2)
[ ] abundant train_ratio=0.4; scarce=0.01; T-Social scarce=0.0001
[ ] Split is computed once (or identically) and reused for all runs
[ ] --run N (default 1; protocol 10) rebuilds the model each time
[ ] run index is not passed to train_test_split
[ ] No --seed flag that changes the split
[ ] Comments cite BWGNN (Tang et al., ICML 2022)
[ ] Homo vs hetero is a model choice, not a second split
[ ] F1: val search linspace(0.05, 0.95, 19) unless the user keeps 0.5 and labels it
What ships with it
3 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.
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.
- 12d ago First seen · 173 lines · 139 tokens per session scan A 355501a5ff5c
graph-fraud is a skill published in the GitHub repository ConmuYan/my-academic-skills (2 stars, last pushed 26d ago), licensed MIT. It adds 139 tokens to every session and 1,876 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
physicsnemo-discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…
hdf5-pde-data-loading
Patterns for loading PDE simulation datasets (PDEBench, PhiFlow, JAX-CFD) from HDF5 files. Handles layout detection (single tensor vs separate variables), spatial/temporal downsampling, multi-variable systems, HuggingFace and DaRUS data sources, and efficient PyTorch DataLoader creation. Use when preparing PDE data…
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…
cellxgene-census-query
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…
single-cell-multi-omics-analysis-scvi
Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics…
rowan
Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve…