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 agentmods add skills/aperivue/medsci-skills/explainabilitynpx skills add Aperivue/medsci-skills --skill explainabilitygit clone --depth 1 https://github.com/Aperivue/medsci-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/aperivue/medsci-skills/explainability)<a href="https://agentmods.dev/skills/aperivue/medsci-skills/explainability"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/explainability.svg" alt="Measured on agentmods" 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 | $0.00150 | $0.01563 |
| Opus 5 | $0.00075 | $0.00781 |
| Sonnet 5 | $0.00030 | $0.00313 |
| Haiku 4.5 | $0.00015 | $0.00156 |
Grade A, and why
explainability 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 6d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explainability Skill
Purpose
A saliency / Grad-CAM heat-map is the most over-interpreted artifact in medical-imaging AI: a colourful map over the lesion is routinely presented as proof the model "looks at the right thing." Adebayo et al. (NeurIPS 2018) showed many saliency methods produce visually convincing maps that are independent of the model's learned weights and of the labels — so they explain nothing. This skill produces an explainability analysis that clears the rigor bar, and audits an existing one, so the map is trustworthy before it reaches a manuscript (CLAIM 2024 / TRIPOD+AI interpretability items).
It sits alongside evaluation in the lane: /architecture-zoo → /preprocess-imaging →
/model-scaffold → /model-validation → /model-evaluation + explainability →
/write-paper + /check-reporting. It integrates captum / pytorch-grad-cam (referenced in the
plan); it does not reimplement them and never runs a model on real patient data.
When to use
- You produced (or are about to produce) saliency / Grad-CAM / attention maps and want them reported to the standard a reviewer expects.
- You want to audit an explainability analysis for the four failure modes below.
When NOT to use
- Discrimination / calibration metrics →
/model-evaluationthen/analyze-stats. - Split or preprocessing leakage →
/model-validation//preprocess-imaging. - LLM/MLLM faithfulness & hallucination →
/mllm-eval. - Reimplementing captum / pytorch-grad-cam → out of scope (this skill wires and audits them).
The four failure modes (what the gate enforces)
- Saliency as validation. A map is attribution, not proof the model is correct or that the relationship is causal. Frame it as "where signal is attributed", never as "the model is right".
- No sanity check. Run the Adebayo model-randomisation and data-randomisation tests. A map that survives neither is uninterpretable; both axes are the minimum bar.
- No quantitative localisation. If you claim the map localises the finding, measure it — IoU / pointing game / Dice against ground-truth masks — do not eyeball a few examples.
- Cherry-picked examples. Report a cohort-level result, not a handful of hand-picked cases.
What ships with it
10 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.
- references/explainability_guide.md 4.1 KB
- scripts/check_explainability_report_challenge/expected/strong.txt 391 B
- scripts/check_explainability_report_challenge/expected/weak.txt 876 B
- scripts/check_explainability_report_challenge/fixture/report_strong.json 238 B
- scripts/check_explainability_report_challenge/fixture/report_weak.json 163 B
- scripts/check_explainability_report_challenge/problem.md 805 B
- scripts/check_explainability_report_challenge/verify.sh 2.0 KB runs code
- scripts/check_explainability_report.py 11 KB runs code
- skill.yml 3.5 KB
- tests/test_explainability_report.sh 4.0 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.
- 6d ago First seen · 110 lines · 150 tokens per session scan A 4d1c082ad483
explainability is a skill published in the GitHub repository Aperivue/medsci-skills (283 stars, last pushed today), licensed MIT. It adds 150 tokens to every session and 1,563 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 2026-08-30.
Other skills, from other repositories
bids
Use this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts, validating compliance, converting DICOM to BIDS, writing metadata sidecars…
bulk-rnaseq
End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and…
torch-geometric
PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torchgeometric, not for general NetworkX analytics or non-graph PyTorch models.
aeon
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard…
esm
Use when working directly with the esm Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.
geniml
Use Geniml for audited local genomic-interval workflows: validate BED and universe contracts, plan Region2Vec or scEmbed runs, inspect model/tokenizer compatibility, and assess consensus universes.